There's also an interesting video by PowerPlayChess here
https://www.youtube.com/watch?v=31UzlgNtQYQ
which covers the games where self capture is allowed. There are some really fascinating tricks that are now possible in that variation.
People have been wailing about chess being dry and full of draws and memorized openings for a century now. Capablanca wanted to swap bisbops and knights to reset opening theory, and Fischer wanted to just randomize the starting positions. I'm probably missing some other people.
All of these attempts failed, because of several reasons:
1) The aforementioned problem of memorizing openings and accumulating draws only occurs at a very, very high level. Even if you're a GM you won't prepare at the level Carlsen et al. do, memorizing entire 30-move games they had against each other twelve years ago.
2) Opening theory moves on and playstyles evolve. AlphaZero shifted the mood from conservative, materialistic, 'computer-like' play to a highly dynamic style that puts an emphasis on piece activity. Just like when we think we got most things figured out, new breakthroughs show we've only barely scratched the surface of what the game has to offer.
3) Most chess players don't see the abundance of draws as a problem. I think it is specifically an American sentiment - in a country where you're either a winner or a loser, the game's failure to rank its top players can be frustrating.
4) Most players see preparation against their opponent as part of competitive play. Think of it as a kind of metagaming. Changing the rules would completely reset that.
5) There's a good chance that any change of rules would aggravate White's marginal first-move advantage. It doesn't matter what the computer says, what matters is how humans play it and how it reflects in the winrates among humans.
That doesn't mean the variants are bad or useless though. Bughouse and suicide chess are crazy fun
960 chess is hugely popular now, and is even being used in tournaments - one of them being today. The only thing that is going out of style in chess is classic chess.
"Even being used in tournaments" is not exactly the same as "hugely popular".
There is some interest, and tournaments are played now and again, sure. However, it's nowhere near the popularity of classic chess, which shows no signs of "going out of style".
To provide some perspective - on lichess.org (one of the most popular sites for online chess; the one where the high-profile tournament you mentioned took place) in June there have been 70,374,749 classic games played. Chess960 accounted for 285,788 games. That's ~250 times less popular.
"Stalemates happen less in 960" - seriously? Why? Do you have any source of that claim? I could believe that draws in general are more rare (lack of opening theory makes equalizing in middle game more difficult). But why would it affect the rate of stalemates specifically?
I am watching Hikaru Nakamura on stream every day, and he does say that 960 will grow, and classic will not. I just take his word for it.
I don't have anything against classic, and as you say, I will probably be playing it forever myself, but from a spectators point of view its more fun if there are less stalemates. There's a lot more room for errors in 960, even among GMs.
Ad 3. This abundance of draws (like #1) only becomes a problem at elite levels, too.
Not to mention just because a game ends with a draw doesn't mean it's a dry and boring draw. A draw can be a fascinating back-and-forth struggle full of tricks and swindles.
Same as many decisive games can actually be yawn-inducing - think 70-moves long, even endgame that comes to a conclusion only because one of the exhausted players finally blunders.
I really doubt (3) and (4). I think most chess players would agree that the draw-ish nature of high level play is boring and uninspiring, and that careful preparation of openings dozens of moves deep isn't the interesting part of the game.
I assure you that drawish games are only boring on the part of the spectators, not on the part of the players. People often struggle epically to catch that half-point, it doesn't feel boring at all when playing from the inside. There are many records of epic draws between titans where both sides played incredibly accurately - see Alekhine - Reti or Korchnoi - Topalov off the top of my mind.
And as I said, people rarely if ever prepare openings 'dozens of moves' deep at all but the absolute top level play.
At this point you have to choose if you want chess to cater to competitive chess players (who are mostly content with the rules as they are) or amateur spectators and organizes (who want to see blood).
Played chess in high school and lost interest in actually playing the more I explored AI... I find it much more fascinating to explore Alpha's games. (Probably I'm also mentally lazier now.)
When I was in college, a Monopoly game appeared on the DEC-10. Playing that for a while completely ruined the game for me. Then someone wrote a bot to play ADVENT, which ruined that, too.
My ability to play chess declined precipitously after I learned how to program, because while thinking of my next move I'd always digress into how to design a program to do the work for me.
I originally wrote the Empire game because it was unbearably tedious to play manually, but the computer took care of the tedium and what was left was the fun.
> I originally wrote the Empire game because it was unbearably tedious to play manually, but the computer took care of the tedium and what was left was the fun.
But would you say the net outcome of this process was a loss or a win for you personally? I mean, I for one never played Monopoly with a computer and yet my perception of the game has certainly changed - not because of technology but because I'm an adult now. I think our stance towards everything always evolves.
In return, you were able to find a new interest through this irk: programming. And I think being passionate about something is what's required to become really good at something, so the fact that your chess playing started to make you think more and deeper about programming was certainly beneficially for the latter.
> would you say the net outcome of this process was a loss or a win for you personally?
Oh, absolutely. It was far beyond my abilities when I started, so I learned how to program with it. It also got me interested in compilers, as the compilers of the day didn't generate good code, Empire was slow, and I naturally assumed I could do much better :-)
Thank you for Empire! I definitely played the Intersel version on my Amiga in maybe '89, and then on my IBM-PC 386, but I believe I also played via Zenith terminal on a PDP-10/11 on Compu-Serv (my Dad was an early employee), in the early '80s.
I loved the game, and made several attempts and coding my own version. Naturally, I went on to love Civilization as well, which has similar game play.
Having turned 50, I feel the same way about many strategy games I play now... it becomes less about the fun and more about the optimization, and how to optimize via program or AI. But I've always been that way... had pages of formulas for optimal planet management in MegaWars III for example.
Empire was fantastic! I whiled away many a computer lab hour on it with some friends. It was probably Empire Deluxe for DOS that I played. I was blown away by how fun it was. Thank you for the fond memories!
Walter, your D source code link on classicempire.com fails with a permission error. Kudos to you for creating what Wikipedia credits as (according to one ranking in 1996) the 8th most popular game of all time.
Considering the power of most portable devices these days have you considered revisiting Empire for an IOS or Android version?
That happens to me a lot of times when playing board games. I tend to start designing the software to play it instead of actually play. So it breaks my concentration in the game.
Shogi is the most complex Chess variant. But seriously. Just play go. New patterns emerge everyday now it seems. The most complex pattern can arise from such simple rules.
I would love to see AlphaZero play go on other manifolds than the plane.
I and some friends attempted to play 3-space go, toroidal go, and go with other mathematical roadblocks a long time ago. It was fun for a few weeks, and we even discovered some interesting properties about where life can exist on a torus, but a computer could do much better. And I'd love to just see the answers.
I think it's obvious. For capture, the definition doesn't change (it's based on no liberties). Depending on the ruleset you don't need more than capture, territory/score/winner can be defined from that.
Conceptually it's fine anyway though, territory is spaces reachable over cardinal directions via empty spaces or dead stones from only one person's living stones.
There are promising chess variants where all draws are eliminated: no black castling or no black short-castling Armageddon (draws are counted as wins for black). I wish they would test them instead of their picks - they are still chess unlike some variants they tested, which are probably too radical if you want to attract current chess players.
I got back to chess few years back, and following scene a bit.
The classical long for chess is basically dead. Its boring, with majority draws (close to solved game - de0incentivizing aggressive play). I am glad there is shift towards shorter time formats.
Shorter time control creates more urgency and allows to play subpar moves to throw off your opponent. Its much more interesting to observe.
Armagedon rules are being used now as tie breakers and there is a lot more discussion about changes/rules tweaks.
I strongly disagree with the assertion that chess is a "close to solved game" in human OTB play in particular.
Top GMs currently will probably score 0/12 against Leela/Stockfish. We see innovations frequently in recent years as we learn from engines themselves, h4/h5 pushes as a simple example, but also in terms of style like favoring rapid development and attacking play.
Yes, draws are frequent but that doesn't mean there is no excitement in long games. Rapid/blitz is damn fun to watch and play but there's a certain, different kind of elegance in carefully considered moves as well.
> I strongly disagree with the assertion that chess is a "close to solved game" in human OTB play in particular.
I meant 90min +30mins classical format. It really is stale and boring to watch. And it seems like its mainly a memory game with some meta counter preparations pre-tournament. Where you develop and memorize lines to counter your opponent. That's what I meant by "close to solved game" - as both players are almost role playing for first 20-30 moves. With tiny variations throughout the tournament.
That results in quite uneventful games, usually same line being played in multiple games.
Anyhow that's just an opinion, if someone enjoys classical more power to them.
Slow chess is not solved by any human; it's broken. It's dead-ended because some better players avoid aggression so they can play short-time tiebreakers instead.
Agreed. Also seem to be not enough incentive to win games. E.g. if Magnus Carlsen thinks he can probably win, he'd settle for a draw if that is the safer alternative. Perhaps it could be changed so that wins count for three points and draws only one. No idea if that would encourage players to become more aggressive.
Draws aren't something that need to be eliminated. There are beautiful draws. Only issue is when draws become too easy (for varying definition of easy). Even today, & even for computers, draws are not too easy. But they are getting easier
Kramnik is the one to talk about computer chess alright... I remember when I was still in school the huge scandal with him going multiple times to the bathroom in his match against then world champion Veselin Topalov (should be around 2005-2006). It caused huge outrage and upset in my native Bulgaria.
On a different note I learned Xiangqi (Chinese chess) this past February and I found it quite interesting and exciting. Rules seem a bit more complicated than chess and I'm not sure how it compares to Shogi for example. Pretty sure Go is still more complex though :)
I believe its very much the arbitrary numbers we gave to pieces that we coded into our brute forced chess AIs that has allowed new chess AIs to be better.
As this article hinted, its understanding of piece value fluctuates based on the rules of the game but also as the game changes. Alpha Zero makes sacrifices human players wouldn't because they're too wedded to the idea that a queen is 9, a rook is 5 and a knight/bishop is 3.5. As flexible as a human mind gets is valuing a rook pair, bishop pair or knights if the position is closed.
This means that Alpha Go destroys the greedy Stockfish because Stockfish counts the numbers but Alpha Go counts the position of the entire board which is much more complicated.
Generally, a queen is considered to be worth more than a rook and a bishop.
Also, knights and bishops are worth the same except they are not. Knights are good in closed play but you can't mate with two knights and a king. Bishops are definitely better when there is more space.
But, the value is just a simplification to help players assess situation. A piece which can't be played actively is worth nothing.
Stockfish evaluates the position of the entire board, e.g. mobility of pieces, how much opposing space they control, etc. But still, the evaluation function is hardcoded and weaker than AlphaZero.
By that I just mean Alpha Go is assuming less about board state than StockFish and other conventional chess AIs do. Evidently the two engines have different assessments which is why Stockfish will greedily lap up a sacrifice by Alpha Zero onto to then lose because of it.
I think that stockfish does more than calculate piece values, it evaluates the strength of positions as a whole and is capable of performing some insane sacrifices itself.
Stockfish parameters aren't arbitrary, hardcoded or static. Vast amount of computational power went into "tuning" those parameters to see which combination of values in which stage etc yields the best outcome. In that sense it's not dissimilar to Alpha Zero except the latter does this a lot more at much higher meta levels.
Not very. It is poetic licence on the part of the writer.
AI had a real impact on how the game was played however. After the advent of computer evaluation, there was a broad consensus that the way to win was to play solid positions. In a way, professional chess became more about not losing than winning. Anish Giri who peaked at number 3 in the world a few years ago is nicknamed the artist because he keeps drawing. Some found that pretty boring.
Funnily, salvation might actually have come from AI. AlphaZero doesn't play boring games and reminded everyone that favoring activity and initiative is a viable strategy.
Still, all things considered, streaming had probably a much bigger impact on chess than AI in the last few years.
Question for those knowledgeable on AI: what sort of game would be easy for a human to understand, but difficult or impossible for a computer to play or easily defeat humans? I imagine one based purely on randomness, like dice, would be one.
I remember reading somewhere that languages like Finnish and Hungarian are difficult for computers to parse, [1] due to their agglutinative grammatical structure. Not sure if that is actually true, but it seems an interesting starting point.
Hanabi only has limited communication. Of course, it's a bit unfair, since a game like Diplomacy requires large amounts of verbal communication, but I think that's the kind of game that's difficult to solve.
Only social games that require you to amuse your fellow participants, like Apples to Apples and the like. Even then, they'll beat people with poor social skills.
Role playing games.
Random dice games, like Yahtzee, are trivial to write programs to play "prefectly" ... it's just stats and your program will avoid both wishful thinking and pattern matching traps humans fall into.
Agglutinative grammar seems to be a difficult nut to crack, and I think Malayalam (my native tongue) is likely the most complex language in that sense. I happened to read "A quantitative analysis of the morphological complexity of Malayalam" (https://kavyamanohar.com/post/malayalam-morphological-comple...) which was published just a few days ago which describes some of the challenges, and has an interesting comparative study of various languages including Finnish and other Indian languages that are known for agglutination, inflection, and derivation from a common root.
Actually, I'd wager that Cards Against Humanity would be one of the games a model would be best at over a human.
There are only a limited number of white cards that could work with any given black card and it could fairly quickly bucket a player into certain types most likely to pick certain cards.
Would it be perfect? No, but that's the nature of the game and with only seven options and no branching paths it doesn't seem like a stretch to say a trained model can trivially beat an average player and challenge a more "advanced" player.
Dixit is a bunch of very different pictures and the goal is to say something about the card you've picked such that some of the other players will know which one it was but not all of them, your opponents are listening to your description and can pick from their own hands of cards. You get points for: Identifying the correct card based on the description when it isn't your turn; Playing a card which people mistook for the correct card when it isn't your turn; Some but not all other players guessing your card when it was your turn.
So that ends up being about shared experiences and culture, because if you share culture with someone you can allude to some element of the picture in a way that's completely opaque to everybody who doesn't share that culture, allowing the "in group" to identify your card while everybody else can't do better than luck.
For an AI there are two interesting challenges. Firstly, in "understanding" the pictures shown on the cards. It's not enough to be like "That's a cat" "That's a book" "That's a tree" you need somehow to compete with a human that thinks "Hmm, that's kinda like the Rapunzel story except it's a bird instead of a princess?" and "The dragon looks happy"
But then the AI also needs cultural context like a human player so it can try to judge good descriptions: "Happy Dragon" is obviously this card, "Cat" might be any of half a dozen cards, how about "I am your father" as a reference to the Cloud City scene that looks a bit like this picture - and so it can try to pick cards that match human descriptions to steal points that way.
Short story writing competitions featuring specific prompts/themes.
SAT test taking.
Short story writing might be more subjective, but the other two are much more objective in nature, and can be easily gamified. AFAIK, AI has a long way to go before it can engage in anything that requires thinking critically.
Not the answer you're looking for, but motor racing and simulations of it.
Sounds counter intuitive, but despite doing fast laps when on the circuit alone, even the best AI racers have difficulty surviving a race distance in close pack racing without crashing.
Roborace, the autonomous racing league in development has barely managed to put two cars on track and doing an overtake safely. A lot of money and state of the art research has gone into this.
I expect that AI will be able to beat humans on the (simulated) race track in a decade or two but we aren't there yet.
There are no racing simulators or even games that have reasonable AI opponents that don't cheat.
I, mid-tier sim racer, have no chance against good AI in hotlapping on track in some popular sims, but all of them either yield or cause a crash that would take them to the stewards (or grave) when racing for position on the same piece of track.
Pro racing team have excellent sims these days but they don't have AI opponents.
Do you have any particular reason to believe that the "AI" you refer to are sophisticated ML models built over the sim, rather than hand crafted bots. You say "don't cheat" which makes me think you're referring to the bots included in the sim. Because an AI that's not built into the game shouldn't have any way to cheat.
Forgive this comparison, but the ai drivers in mario kart games also cheat, but aren't particularly representative of current state ML tech. There's likely no ML involved in them at all. There's not much in the way of actual attempts to do this with ML either so it's not proof either way (especially on new untrained courses).
No, they are not sophisticated ML models. Such things don't exist in this space as far as I know.
The ones that cheat are in racing games. The hardcore sims that have AI bots don't usually cheat, and they are the ones that are fast by themselves but hopeless and/or dangerous in a pack.
Roborace is the only place where this kind of research has been done, and after many years and millions of dollars they're past their first baby steps, but still learning to walk before they can run.
I don’t know much bridge so please correct me if I’m wrong, but isn’t that “cheating” basically applying steganography to game moves? It’s not like touching your ear at the right time or some other kind of back channel. It’s all represented by game moves. That sounds tractable for an algorithm.
Well yes, that and actual cheating (the competitive scene if rife with cheating of all kinds).
If AI teammates were allowed to have a pre-developed, shared model between them for communication so the other automatically "knows" what the others moves mean then it would be closer to fair grounds but that's considered cheating even though human teammates do the same thing.
I imagine one could apply the semantics of a leadership election algorithm and a recognizer neural net in each AI player to let them develop their messaging in game. If the AI were permitted to store temporary state through the course of a tournament or with a practice round (human players practice too) then I don’t see why it couldn’t work.
I haven't been in the contract-bridge scene in a long time, but had a friend who was competitive at the regional-level, and the impression I got was that partner-signalling was hard to get away with just because opponents would recognize abnormal results so quickly; at that level you would regularly face opponents who could tell you every contract you had bid against them and what the result was from memory.
On the other hand, I worked at a US Team Trials championship game, and the two tables were in separate rooms, with a diagonal partition across the table and completely silent bidding. Presumably they wouldn't go through such gymnastics if cheating weren't a concern. Perhaps the stakes are too low at the regional level (or those who are good enough to get away with it quickly progress to a higher level?).
What? Bidding is all about sharing information with your partner about what's in your hand. There's nothing cheating about that. Cheating would be if you had some side channel that was not the explicit information you were allowed to share as part of the process - e.g. if you were playing online and relaying your bids as "one - clubs" meant something different to your partner than saying "1 - clubs".
Sort of, except you have to tell your opponents what your algorithm is. Like you can invent a system where an opening bid of "one heart" means "I have exactly three aces" (as opposed to the conventional meaning of "I have a reasonably strong hand with hearts as my longest suit"), but you can't keep that meaning secret.
>I remember reading somewhere that languages like Finnish and Hungarian are difficult for computers to parse
I wonder how much of that is due to AI researchers being speakers of Indo-European languages and not being able to wrap their mind around languages outside that family
If the AI needs to interpret the rules of a card based on it's text and figure out how to use them, it would indeed be a very difficult challenge.
If the AI can simply learn how to play the game with a predefined deck, it'll probably do just fine, outperforming humans but not all the time due to random chance.
I think you'd have to go even narrower by predefined the AI's opponent's deck as well before you'd get an AI that consistently outperformed humans. Even the most all in combo or burn deck will drop lose percentage points if they don't take into account what they're playing against and what hate cards to play around.
By predefined, I meant comprised from a pool of cards that the AI is familiar with. But now that I think about it, it is a much more interesting problem. Most of the big name bots, like the dota one, do have some model for picking a character. But the scope of choices is very limited to the point where even if it's "one model" it can have a large space dedicated to specifically that character. Would current techniques be sufficient to, given enough training data on each individual card, be able to compose a deck to fit arbitrarily assigned constraints and find a way to play it effectively? I don't know, but the answer sounds a lot closer to the idea of "strategy" that researchers are trying get at but missing the mark on in Starcraft and what not.
I have no idea how they'd handle that. It's a great way to prevent the bot from learning a single dominant strategy and trying to just execute it perfectly.
This is a really interesting - and I think, important - question although people ruling stuff out of bounds for AI do have a habit of becoming proven wrong - the classic recent example being Go.
My assumption would be games or activities that are NOT heavily based in pattern finding, maths, statistics, categorising, memory etc.
I think it is more useful perhaps to consider the motivation for game playing which is completely different (at present) for humans/animals compared to computers.
We play because it is fun, or to bond, or to improve social status, make money, whatever.
Computers play because that is what they are told to do.
Starting variation (like Arimaa), takes opening books off the table. In general, high branching factors (possible moves at any situation) are more difficult. Humans have an intuitive sense for which moves are reasonable at any situation, or whether a line of play is productive. Branching factor is part of why Go was so much harder than chess. Hidden information is hard: computers are not good at the "thinking in another's shoes" and inferring hidden facts from known ones, or are too easily tricked by ploys. Poker is an extremely simple hidden information game, but as I understand it, the AIs are still behind humans. Ease of position evaluation is also very important to computers. No one has made a general Magic The Gathering AI that is even mediocre at the game, because it is extremely difficult to heuristically evaluate a general boardstate. There are many non-linearities, and the value of cards is heavily situation and strategy dependent.
Not just "There's an AI which is very good at it" there is literally a fixed strategy I can reveal in advance and that strategy will statistically break even against an equally efficient strategy or else gradually take all your chips if you don't have a similar perfect strategy. Even though you know exactly what the strategy is, you can't beat it anyway.
At No Limit the clear champion is AI. Pluribus, Libratus and Deepstack all play clearly better poker, it's not practical to conceive a "solved" or even "near solved" like Cepheus strategy for No Limit, but the AI is tireless and it's disheartening for humans to just find every strategy countered so I expect them to get worse not better.
I don't expect any further exhibition type matches for AI versus professionals at poker because of this success.
Now, full ring is different, but largely because of the social dynamics. If you're at a table with six humans and one AI, obviously all of the humans will co-operate to force out the AI since the alternative is the AI wins. So that's not a very interesting problem.
Recently there has been a growing interest in developing AI for cooperative games, like Hanabi. I believe the challenge originated from a paper by Google Brain/DeepMind [1], but several other groups have tackled it, including Facebook AI Research [2].
That comic is from 2012, and since then Arimaa, Go and Poker have moved solidly into the "Computers Can Beat Top Humans" category. Jeopardy would probably be there too if there was a consistent effort behind it. I think the Starcraft AI is pretty good these days, but people argue over things like APM restrictions.
I think it would be interesting to look for games that are the same kind of game as chess or Go (zero-sum games without randomness), but are harder for Alpha Zero than people. Something where it's hard to learn through self-play alone.
Even still, AIs are not able to "figure out" exploration heavy games, like montezuma's revenge [1]
I suspect games that will give ai the most trouble: games with super sparse signals or ambiguous directions (others mention RPGs, and that tracks)
Games that are hard to simulate will be hard from a training perspective (I think both starcraft and dota2 needed patches to give the AIs reasonable tools to understand the game)
At one point, before go was solved, it seemed like maybe adding significant depth or randomness to a game might make it "hard", but now I'm more convinced that difficulty simulating & exploring tends to be a bigger factor
This is a slight tangent to the article, but in the hope HN readers will find this as fascinating as I have recently...
There's a three-way battle developing between AlphaZero (as described in the article, courtesy of DeepMind), LCZero[5] (derived from LeelaZero[1] -- an open source interpretation of the same principles as AZ), and Stockfish[2] (a long-standing open source chess engine that has recently begun including neural network support).
The 'Top Chess Engine Championship'[3] seems to be a good way to follow the latest news; they also stream matches live on their website[4] (it is quite an information-dense site).
You can play against an up-to-date implementation of Stockfish in your browser -- no registration or signup required -- at https://lichess.org
LeelaZero is strictly used for the Go AI nowadays, the chess version changed their name to LC0 (or Leela Chess Zero, or LCZero), and the website is at [0]
AlphaZero is not involved in any battle with LC0 or Stockfish, as no one outside of Deepmind has accessed to it. The battle for chess supreme is between LC0 and Stockfish, with both trading blows pretty much every update :-)
Very recently, with the advent of the NNUE evaluation and it's incorporation into stockfish, it is the undisputed champion over all others by a very significant margin.
It even beats out lc0 running on an RTX 2080 while itself running in single-threaded mode (it scales well in strength up to at least 32 threads, beginning to taper off from there)
The recently released Stockfish 12 with neural network evaluation seems to be the clear winner, combining the best of both worlds and handily beating classical Stockfish 11 and LC0 (which were pretty evenly matched on typical hardware).
A summary to undo the clickbait: AI is making chess beautiful by making it easy to check how new rules affect playability. Rule changes suggested in the article are:
Even if a new game mode is found to enhance gameplay, AI would master these variations quickly reducing the novelty of them.
The best attempt I've seen is Fisher random chess which attempts to create so many unique starting positions that memorizing openings becomes impossible. It ends up leading to really unique situations, and in some cases even a first move advantage for black.
I think the idea is that once AI "solves" a game mode it becomes easier for humans to get better faster by learning from the AI and therefore less fun.
For example, chess players used to practice (or invent) novel openings to surprise their opponents. Now that AI has explored such a huge range of the game space it can simply show you the optimal moves for each opening. So for humans there's less exploration and more memorization. You're simply trying to follow a path that AI has paved rather than find a new path.
It's kind of like how tic tac toe is fun as a kid until you discover how you can tie everytime. Even with these new rules AI would rapidly find optimal strategies that humans would then race to replicate.
I think that's a bit harsh, there's more to the article than that - chess players talking about seeing the computer evolve techniques that have been discovered over hundreds of years of chess, for but one.
An important piece of context here is that making a living by playing chess competitively is close to nil, so many even top players like Kramnik end up taking consulting/PR jobs like this in order to pay the bills. I have a hard time believing Kramnik actually believes (or said directly) that AI ruined chess. My read is that he's not really promoting changes to the rules of chess as much as he's trying to build support for new types of chess variants.
It's true that the highest levels of play include teams of researchers and computers that develop 30+ move preparation, but what we're also seeing as a result of that are games that are more precise, which IMO is a fundamental component of chess "beauty". Some notable games that were deemed "beautiful" in the past are now seen as less-beautiful as it became apparent that play was suboptimal. Chess beauty now is less about flashy combinations and more about qualities of a position and reverse engineering the "logic" behind certain AI moves, which is still great but admittedly requires more of an investment on learning the game than a spectator might care about.
That framing, though, leaves out the massive benefit that AI has had in training and improving new players. It used to be that you needed to hire a chess master to play against and learn from in order to improve. Now your phone can easily give you a challenge of master-level strength, as well as analyze your games over the board to look for improvements.
> Chess beauty now is less about flashy combinations and more about qualities of a position
No it's the opposite. Since the advent of strong computer programs it has become clear that there are tactical intricacies in lots of positions that have long been overlooked by everyone, including top players. Gambits that everyone thought should not be accepted because it would give away a too strong positional advantage turned out to be winnable by clever defence moves. End games that were thought to be draws turned out to be winnable by although sometimes it would take more than 100 moves.
The bottom line is that the tactical part of chess is deeper than most people thought.
But would you call someone who wins a supposedly drawn endgame after 100 moves a tactical player or positional player? No one I know would claim that what happened on the 100th move was a tactic. It was 90+ moves of jockeying for position.
A human can't normally predict out 100 moves of optimal play, so that's why it is jockeying instead of being part of an intricate plan.
I mean, it does bring the question, do you play a game for the experience or solely to win?
I play games for the experience, the world's best chess player probably gets a thrill from being the best and winning. Obviously both experiences are legitimate and in competitive chess, studying historical games to learn patterns has always been a thing, so who's to say that studying scenarios 'solved' by a computer is really any different? Possibly there's a little less romance because a human didn't do it on their own? It doesn't appeal to me personally, but neither did studying chess moves. It really looks like a question of scale of preparation to me.
Lichess has great variants to play. If you haven't tried crazyhorse or multi-player version bughouse, highly recommend it. In crazyhorse you can put captured enemy anywhere on the board as your own piece.
Likewise in bughouse, you play with a partner (where you are opposite colors) against another team. You each play your own game against the opponent but each opponent piece you capture you can give to your partner to place on their board and vice versa. First person to win the game wins for their team. It requires good communication and a different strategies than traditional chess as you need to account for two games and the flow of pieces on both boards.
Also, if you really want to dive into the crazyhouse idea you can try learning Shogi which is effectively the Japanese version of western chess and has the drop rule and interesting promotion mechanics.
I did't like the article in the sense that AI hasn't ruined chess. Its more popular than ever, but the focus has moved to shorter time controls...which can be quite exciting to watch. I watch chess tournaments on twitch.tv with two grand masters commentating...and honestly, its like watching a godly hockey match.
That said, I'd like to see some of these variations get implemented on chess.com. A lot of the variations (aside from 960) are a bit silly feeling (e.g. a variation where when you take a piece, all pieces within a 1 square radius get blown to smithereens).
> In chess, AlphaZero initially doesn’t know it can take an opponent’s pieces. Over hours of high-speed play against successively more powerful incarnations of itself, it becomes more skilled, and to some eyes more natural, than prior chess engines.
'doesn’t know it can take an opponent’s pieces' - really? How would the world be different if it did 'know'?
I know this is kind of a nitpick, but I'm tired of all the metaphors in tech journalism that hold no informational value. I think giving a sense of false understanding is worse than just saying nothing at all.
I think it's an imprecise way of saying that AlphaZero isn't given the game rules, so it doesn't know the difference between legal and illegal moves, and also that before any training it would evaluate a caputure no differently than any other move.
> isn't given the game rules, so it doesn't know the difference between legal and illegal moves
But it does have some way to determine a list of legal moves from any given state, and a way to determine whether a state is winning. To me, that's being 'given the game rules'.
> before any training it would evaluate a capture no differently than any other move.
It's weird that they the start of this article seems to imply that AI has taken the joy out of chess. I guess I was only a kid for the Deep Blue vs. Kasparov days so maybe I don't know any different, but to me fundamentally chess is joyful because it's a sport. It's not about trying to be the best algorithm in the world, it's about trying to put out strong consistent performance on the spot in a game. Sure, your moves won't be as good as a computer's but that doesn't take the joy out of making them try to be as good as possible.
I invented a game called Arimaa that could be played with a chess set but the rules were very different to make it harder for computer. I put up a $10k challenge to develop an AI that could defeat the top human players. A challenge match was run every year from 2004 to 2015 when it was finally claimed (one year before AI took over Go). There was a variant of Arimaa that I didn't go with since the games did not seem that interesting. It was the same as current Arimaa, but without any trap squares. So no pieces were captured and the game seem to take longer to finish, but I think it may have been a more strategic version (less tactics). I still wonder sometimes if that would have been helped the humans stay ahead a bit longer. I avoided that version since I was not sure if it could lead to deadlock positions. Play testing to check for flaws especially at high level play would be way to much effort for humans. It would be less effort to have an AI check the game rules. Although there is still a big cost to doing that. The AI researchers in the Arimaa community have recently developed an AI that has learned to play Arimaa through self play. They have also brought down the cost of training from about $1 million to about $1 thousand. If anyone is interested, there is a discord channel where we discuss this kind of stuff https://discord.gg/XTAcDjR
More information about the Arimaa game as well as a gameroom where you can play it available here: http://arimaa.com/
138 comments
[ 9.8 ms ] story [ 206 ms ] threadhttps://www.chess.com/news/new-alphazero-paper-explores-ches...
All of these attempts failed, because of several reasons:
1) The aforementioned problem of memorizing openings and accumulating draws only occurs at a very, very high level. Even if you're a GM you won't prepare at the level Carlsen et al. do, memorizing entire 30-move games they had against each other twelve years ago.
2) Opening theory moves on and playstyles evolve. AlphaZero shifted the mood from conservative, materialistic, 'computer-like' play to a highly dynamic style that puts an emphasis on piece activity. Just like when we think we got most things figured out, new breakthroughs show we've only barely scratched the surface of what the game has to offer.
3) Most chess players don't see the abundance of draws as a problem. I think it is specifically an American sentiment - in a country where you're either a winner or a loser, the game's failure to rank its top players can be frustrating.
4) Most players see preparation against their opponent as part of competitive play. Think of it as a kind of metagaming. Changing the rules would completely reset that.
5) There's a good chance that any change of rules would aggravate White's marginal first-move advantage. It doesn't matter what the computer says, what matters is how humans play it and how it reflects in the winrates among humans.
That doesn't mean the variants are bad or useless though. Bughouse and suicide chess are crazy fun
Stalemates happen less in 960.
There is some interest, and tournaments are played now and again, sure. However, it's nowhere near the popularity of classic chess, which shows no signs of "going out of style".
To provide some perspective - on lichess.org (one of the most popular sites for online chess; the one where the high-profile tournament you mentioned took place) in June there have been 70,374,749 classic games played. Chess960 accounted for 285,788 games. That's ~250 times less popular.
"Stalemates happen less in 960" - seriously? Why? Do you have any source of that claim? I could believe that draws in general are more rare (lack of opening theory makes equalizing in middle game more difficult). But why would it affect the rate of stalemates specifically?
I don't have anything against classic, and as you say, I will probably be playing it forever myself, but from a spectators point of view its more fun if there are less stalemates. There's a lot more room for errors in 960, even among GMs.
I've been watching a lot of Hikaru's streams since PogChamps put him on my radar and he is a very entertaining player IMO.
Ad 3. This abundance of draws (like #1) only becomes a problem at elite levels, too.
Not to mention just because a game ends with a draw doesn't mean it's a dry and boring draw. A draw can be a fascinating back-and-forth struggle full of tricks and swindles.
Same as many decisive games can actually be yawn-inducing - think 70-moves long, even endgame that comes to a conclusion only because one of the exhausted players finally blunders.
And as I said, people rarely if ever prepare openings 'dozens of moves' deep at all but the absolute top level play.
At this point you have to choose if you want chess to cater to competitive chess players (who are mostly content with the rules as they are) or amateur spectators and organizes (who want to see blood).
Wonder if we could go one further and have tournaments where the rules changed to a different ordered variation after a set number of moves.
Now that would be mind bending.
My ability to play chess declined precipitously after I learned how to program, because while thinking of my next move I'd always digress into how to design a program to do the work for me.
I originally wrote the Empire game because it was unbearably tedious to play manually, but the computer took care of the tedium and what was left was the fun.
This is also the premise behind Factorio.
In return, you were able to find a new interest through this irk: programming. And I think being passionate about something is what's required to become really good at something, so the fact that your chess playing started to make you think more and deeper about programming was certainly beneficially for the latter.
Oh, absolutely. It was far beyond my abilities when I started, so I learned how to program with it. It also got me interested in compilers, as the compilers of the day didn't generate good code, Empire was slow, and I naturally assumed I could do much better :-)
I loved the game, and made several attempts and coding my own version. Naturally, I went on to love Civilization as well, which has similar game play.
Having turned 50, I feel the same way about many strategy games I play now... it becomes less about the fun and more about the optimization, and how to optimize via program or AI. But I've always been that way... had pages of formulas for optimal planet management in MegaWars III for example.
Considering the power of most portable devices these days have you considered revisiting Empire for an IOS or Android version?
http://classicempire.com/
I'll announce it here:
https://twitter.com/ClassicEmpire
It'll likely need some minor work to work with the latest D compiler, attend to that in a bit.
I and some friends attempted to play 3-space go, toroidal go, and go with other mathematical roadblocks a long time ago. It was fun for a few weeks, and we even discovered some interesting properties about where life can exist on a torus, but a computer could do much better. And I'd love to just see the answers.
I would imagine the definition of surround would have to be modified accordingly.
Conceptually it's fine anyway though, territory is spaces reachable over cardinal directions via empty spaces or dead stones from only one person's living stones.
The classical long for chess is basically dead. Its boring, with majority draws (close to solved game - de0incentivizing aggressive play). I am glad there is shift towards shorter time formats.
Shorter time control creates more urgency and allows to play subpar moves to throw off your opponent. Its much more interesting to observe.
Armagedon rules are being used now as tie breakers and there is a lot more discussion about changes/rules tweaks.
So who knows what next year will bring.
Top GMs currently will probably score 0/12 against Leela/Stockfish. We see innovations frequently in recent years as we learn from engines themselves, h4/h5 pushes as a simple example, but also in terms of style like favoring rapid development and attacking play.
Yes, draws are frequent but that doesn't mean there is no excitement in long games. Rapid/blitz is damn fun to watch and play but there's a certain, different kind of elegance in carefully considered moves as well.
I meant 90min +30mins classical format. It really is stale and boring to watch. And it seems like its mainly a memory game with some meta counter preparations pre-tournament. Where you develop and memorize lines to counter your opponent. That's what I meant by "close to solved game" - as both players are almost role playing for first 20-30 moves. With tiny variations throughout the tournament.
That results in quite uneventful games, usually same line being played in multiple games.
Anyhow that's just an opinion, if someone enjoys classical more power to them.
On a different note I learned Xiangqi (Chinese chess) this past February and I found it quite interesting and exciting. Rules seem a bit more complicated than chess and I'm not sure how it compares to Shogi for example. Pretty sure Go is still more complex though :)
https://cse.buffalo.edu/~regan/chess/fidelity/Elista2006.htm...
As this article hinted, its understanding of piece value fluctuates based on the rules of the game but also as the game changes. Alpha Zero makes sacrifices human players wouldn't because they're too wedded to the idea that a queen is 9, a rook is 5 and a knight/bishop is 3.5. As flexible as a human mind gets is valuing a rook pair, bishop pair or knights if the position is closed.
This means that Alpha Go destroys the greedy Stockfish because Stockfish counts the numbers but Alpha Go counts the position of the entire board which is much more complicated.
Also, knights and bishops are worth the same except they are not. Knights are good in closed play but you can't mate with two knights and a king. Bishops are definitely better when there is more space.
But, the value is just a simplification to help players assess situation. A piece which can't be played actively is worth nothing.
Recently Stockfish introduced neural network evaluation.
https://blog.stockfishchess.org/post/625828091343896577/intr...
AI had a real impact on how the game was played however. After the advent of computer evaluation, there was a broad consensus that the way to win was to play solid positions. In a way, professional chess became more about not losing than winning. Anish Giri who peaked at number 3 in the world a few years ago is nicknamed the artist because he keeps drawing. Some found that pretty boring.
Funnily, salvation might actually have come from AI. AlphaZero doesn't play boring games and reminded everyone that favoring activity and initiative is a viable strategy.
Still, all things considered, streaming had probably a much bigger impact on chess than AI in the last few years.
I remember reading somewhere that languages like Finnish and Hungarian are difficult for computers to parse, [1] due to their agglutinative grammatical structure. Not sure if that is actually true, but it seems an interesting starting point.
[1] Discussion sort of about this: https://news.ycombinator.com/item?id=21572261
Genres that would be difficult: - any game based on recognizing images (the first example that pops in my mind is codenames)
- social deduction like werewolf
Pictionary might be harder.
[0] https://en.m.wikipedia.org/wiki/Arimaa
At this point, I'd say that AI can't really play collaborative games well, like Diplomacy. They also struggle in continuous games.
Role playing games.
Random dice games, like Yahtzee, are trivial to write programs to play "prefectly" ... it's just stats and your program will avoid both wishful thinking and pattern matching traps humans fall into.
E.g. "I'm sorry I haven't a Clue"[1] or something like Cards Against Humanity.
Though I imagine someone is trying to apply GPT-3 to these sorts of games already.
Beyond that, any sort of narrative based RPG or exploration game (e.g. legend of Zelda) would be hard to do 'properly', i.e. without scripting a bot.
[1] https://en.m.wikipedia.org/wiki/I%27m_Sorry_I_Haven%27t_a_Cl...
Dixit is a bunch of very different pictures and the goal is to say something about the card you've picked such that some of the other players will know which one it was but not all of them, your opponents are listening to your description and can pick from their own hands of cards. You get points for: Identifying the correct card based on the description when it isn't your turn; Playing a card which people mistook for the correct card when it isn't your turn; Some but not all other players guessing your card when it was your turn.
So that ends up being about shared experiences and culture, because if you share culture with someone you can allude to some element of the picture in a way that's completely opaque to everybody who doesn't share that culture, allowing the "in group" to identify your card while everybody else can't do better than luck.
For an AI there are two interesting challenges. Firstly, in "understanding" the pictures shown on the cards. It's not enough to be like "That's a cat" "That's a book" "That's a tree" you need somehow to compete with a human that thinks "Hmm, that's kinda like the Rapunzel story except it's a bird instead of a princess?" and "The dragon looks happy"
But then the AI also needs cultural context like a human player so it can try to judge good descriptions: "Happy Dragon" is obviously this card, "Cat" might be any of half a dozen cards, how about "I am your father" as a reference to the Cloud City scene that looks a bit like this picture - and so it can try to pick cards that match human descriptions to steal points that way.
Short story writing competitions featuring specific prompts/themes.
SAT test taking.
Short story writing might be more subjective, but the other two are much more objective in nature, and can be easily gamified. AFAIK, AI has a long way to go before it can engage in anything that requires thinking critically.
Sounds counter intuitive, but despite doing fast laps when on the circuit alone, even the best AI racers have difficulty surviving a race distance in close pack racing without crashing.
Roborace, the autonomous racing league in development has barely managed to put two cars on track and doing an overtake safely. A lot of money and state of the art research has gone into this.
I expect that AI will be able to beat humans on the (simulated) race track in a decade or two but we aren't there yet.
I, mid-tier sim racer, have no chance against good AI in hotlapping on track in some popular sims, but all of them either yield or cause a crash that would take them to the stewards (or grave) when racing for position on the same piece of track.
Pro racing team have excellent sims these days but they don't have AI opponents.
Forgive this comparison, but the ai drivers in mario kart games also cheat, but aren't particularly representative of current state ML tech. There's likely no ML involved in them at all. There's not much in the way of actual attempts to do this with ML either so it's not proof either way (especially on new untrained courses).
The ones that cheat are in racing games. The hardcore sims that have AI bots don't usually cheat, and they are the ones that are fast by themselves but hopeless and/or dangerous in a pack.
Roborace is the only place where this kind of research has been done, and after many years and millions of dollars they're past their first baby steps, but still learning to walk before they can run.
Of course you could argue that it is a difficult game for humans to understand as well =) So it might not fit exactly what you prompted for.
https://en.wikipedia.org/wiki/Computer_bridge
If AI teammates were allowed to have a pre-developed, shared model between them for communication so the other automatically "knows" what the others moves mean then it would be closer to fair grounds but that's considered cheating even though human teammates do the same thing.
On the other hand, I worked at a US Team Trials championship game, and the two tables were in separate rooms, with a diagonal partition across the table and completely silent bidding. Presumably they wouldn't go through such gymnastics if cheating weren't a concern. Perhaps the stakes are too low at the regional level (or those who are good enough to get away with it quickly progress to a higher level?).
Sort of, except you have to tell your opponents what your algorithm is. Like you can invent a system where an opening bid of "one heart" means "I have exactly three aces" (as opposed to the conventional meaning of "I have a reasonably strong hand with hearts as my longest suit"), but you can't keep that meaning secret.
>I remember reading somewhere that languages like Finnish and Hungarian are difficult for computers to parse
I wonder how much of that is due to AI researchers being speakers of Indo-European languages and not being able to wrap their mind around languages outside that family
If the AI needs to interpret the rules of a card based on it's text and figure out how to use them, it would indeed be a very difficult challenge.
If the AI can simply learn how to play the game with a predefined deck, it'll probably do just fine, outperforming humans but not all the time due to random chance.
I have no idea how they'd handle that. It's a great way to prevent the bot from learning a single dominant strategy and trying to just execute it perfectly.
https://www.youtube.com/watch?v=MHTizZ_XcUM
https://en.wikipedia.org/wiki/Diplomacy_(game)
My assumption would be games or activities that are NOT heavily based in pattern finding, maths, statistics, categorising, memory etc.
I think it is more useful perhaps to consider the motivation for game playing which is completely different (at present) for humans/animals compared to computers.
We play because it is fun, or to bond, or to improve social status, make money, whatever.
Computers play because that is what they are told to do.
The state of the art for Poker goes like this:
Heads Up Limit Texas Hold 'Em is effectively solved.
http://poker.srv.ualberta.ca/
Not just "There's an AI which is very good at it" there is literally a fixed strategy I can reveal in advance and that strategy will statistically break even against an equally efficient strategy or else gradually take all your chips if you don't have a similar perfect strategy. Even though you know exactly what the strategy is, you can't beat it anyway.
At No Limit the clear champion is AI. Pluribus, Libratus and Deepstack all play clearly better poker, it's not practical to conceive a "solved" or even "near solved" like Cepheus strategy for No Limit, but the AI is tireless and it's disheartening for humans to just find every strategy countered so I expect them to get worse not better.
I don't expect any further exhibition type matches for AI versus professionals at poker because of this success.
Now, full ring is different, but largely because of the social dynamics. If you're at a table with six humans and one AI, obviously all of the humans will co-operate to force out the AI since the alternative is the AI wins. So that's not a very interesting problem.
[1] https://www.sciencedirect.com/science/article/pii/S000437021...
[2] https://arxiv.org/pdf/1912.02318v1.pdf
https://xkcd.com/1002/
That comic is from 2012, and since then Arimaa, Go and Poker have moved solidly into the "Computers Can Beat Top Humans" category. Jeopardy would probably be there too if there was a consistent effort behind it. I think the Starcraft AI is pretty good these days, but people argue over things like APM restrictions.
I suspect games that will give ai the most trouble: games with super sparse signals or ambiguous directions (others mention RPGs, and that tracks)
Games that are hard to simulate will be hard from a training perspective (I think both starcraft and dota2 needed patches to give the AIs reasonable tools to understand the game)
At one point, before go was solved, it seemed like maybe adding significant depth or randomness to a game might make it "hard", but now I'm more convinced that difficulty simulating & exploring tends to be a bigger factor
[1] https://openai.com/blog/learning-montezumas-revenge-from-a-s... It gets it but hard to make a general ai that understands it and the other atari games
There's a three-way battle developing between AlphaZero (as described in the article, courtesy of DeepMind), LCZero[5] (derived from LeelaZero[1] -- an open source interpretation of the same principles as AZ), and Stockfish[2] (a long-standing open source chess engine that has recently begun including neural network support).
The 'Top Chess Engine Championship'[3] seems to be a good way to follow the latest news; they also stream matches live on their website[4] (it is quite an information-dense site).
You can play against an up-to-date implementation of Stockfish in your browser -- no registration or signup required -- at https://lichess.org
[1] - https://zero.sjeng.org/
[2] - https://stockfishchess.org/
[3] - https://en.wikipedia.org/wiki/Top_Chess_Engine_Championship
[4] - https://tcec-chess.com/
[5] - https://www.lczero.org/
Edit: correct LeelaZero -> LCZero
https://tcec-chess.com/articles/Sufi_18_-_Sadler.pdf
AlphaZero is not involved in any battle with LC0 or Stockfish, as no one outside of Deepmind has accessed to it. The battle for chess supreme is between LC0 and Stockfish, with both trading blows pretty much every update :-)
[0] https://lczero.org/
It even beats out lc0 running on an RTX 2080 while itself running in single-threaded mode (it scales well in strength up to at least 32 threads, beginning to taper off from there)
- No castling
- Allowing self capture
- Pawns can move sideways
- Pawns can move 2 squares at a time
https://youtu.be/i-oDOJlWBTw?t=1849
"That's castling sweetheart... It's an advanced level manoeuvre, they added it in the last patch."
The best attempt I've seen is Fisher random chess which attempts to create so many unique starting positions that memorizing openings becomes impossible. It ends up leading to really unique situations, and in some cases even a first move advantage for black.
For example, chess players used to practice (or invent) novel openings to surprise their opponents. Now that AI has explored such a huge range of the game space it can simply show you the optimal moves for each opening. So for humans there's less exploration and more memorization. You're simply trying to follow a path that AI has paved rather than find a new path.
It's kind of like how tic tac toe is fun as a kid until you discover how you can tie everytime. Even with these new rules AI would rapidly find optimal strategies that humans would then race to replicate.
It's his story on what happened around Deep Blue.
It's true that the highest levels of play include teams of researchers and computers that develop 30+ move preparation, but what we're also seeing as a result of that are games that are more precise, which IMO is a fundamental component of chess "beauty". Some notable games that were deemed "beautiful" in the past are now seen as less-beautiful as it became apparent that play was suboptimal. Chess beauty now is less about flashy combinations and more about qualities of a position and reverse engineering the "logic" behind certain AI moves, which is still great but admittedly requires more of an investment on learning the game than a spectator might care about.
That framing, though, leaves out the massive benefit that AI has had in training and improving new players. It used to be that you needed to hire a chess master to play against and learn from in order to improve. Now your phone can easily give you a challenge of master-level strength, as well as analyze your games over the board to look for improvements.
No it's the opposite. Since the advent of strong computer programs it has become clear that there are tactical intricacies in lots of positions that have long been overlooked by everyone, including top players. Gambits that everyone thought should not be accepted because it would give away a too strong positional advantage turned out to be winnable by clever defence moves. End games that were thought to be draws turned out to be winnable by although sometimes it would take more than 100 moves. The bottom line is that the tactical part of chess is deeper than most people thought.
But would you call someone who wins a supposedly drawn endgame after 100 moves a tactical player or positional player? No one I know would claim that what happened on the 100th move was a tactic. It was 90+ moves of jockeying for position.
A human can't normally predict out 100 moves of optimal play, so that's why it is jockeying instead of being part of an intricate plan.
I mean, it does bring the question, do you play a game for the experience or solely to win?
I play games for the experience, the world's best chess player probably gets a thrill from being the best and winning. Obviously both experiences are legitimate and in competitive chess, studying historical games to learn patterns has always been a thing, so who's to say that studying scenarios 'solved' by a computer is really any different? Possibly there's a little less romance because a human didn't do it on their own? It doesn't appeal to me personally, but neither did studying chess moves. It really looks like a question of scale of preparation to me.
Likewise in bughouse, you play with a partner (where you are opposite colors) against another team. You each play your own game against the opponent but each opponent piece you capture you can give to your partner to place on their board and vice versa. First person to win the game wins for their team. It requires good communication and a different strategies than traditional chess as you need to account for two games and the flow of pieces on both boards.
That said, I'd like to see some of these variations get implemented on chess.com. A lot of the variations (aside from 960) are a bit silly feeling (e.g. a variation where when you take a piece, all pieces within a 1 square radius get blown to smithereens).
'doesn’t know it can take an opponent’s pieces' - really? How would the world be different if it did 'know'?
I know this is kind of a nitpick, but I'm tired of all the metaphors in tech journalism that hold no informational value. I think giving a sense of false understanding is worse than just saying nothing at all.
But it does have some way to determine a list of legal moves from any given state, and a way to determine whether a state is winning. To me, that's being 'given the game rules'.
> before any training it would evaluate a capture no differently than any other move.
That's a good way to say it!
No it doesn't. That's the Zero part.
More information about the Arimaa game as well as a gameroom where you can play it available here: http://arimaa.com/