Neat, I don't understand what they mean by having embedded a reward video into the set. Is that a video where copying the behaviour will deliver victory?
I can see where you're coming from, the title definitely made me initially feel like it was going to be about getting satisfaction from watching other people play a game or something like that.
Are audio cues also analyzed here? ie: "We observe that use of the audio signal in CMC results in more
emphasis being placed on key items and their location in the inventory"
Hmm I was more under the impression it was for context, in other words creating/executing strategies based on what audio cues were received (like when a key or coin is acquired) and keeping tabs of what actions the user performed after that point.
11 comments
[ 6.1 ms ] story [ 92.6 ms ] threadThe AI is rewarded if at each checkpoint the state vector its produced is sufficiently aligned with the videos.
I guess that's the initial training to deal with sparse rewards.
Also interesting assumption to say "harder = fewer rewards". Probably doesn't always apply but is a good generalization.