[–] giacaglia 7y ago ↗ It would be interesting to know if there were similar techniques employed for AlphaStar and AlphaGo, with DeepMind's use of LSTMs, etc... [–] mercautoe 7y ago ↗ From my understanding AlphaStar used a LSTM to determine the actions of its agents, but it had a transformer to draw attention to a subset of the inputs [–] maximur 7y ago ↗ It would be nice to get an in-depth overview of the techniques used behind AlphaStar...
[–] mercautoe 7y ago ↗ From my understanding AlphaStar used a LSTM to determine the actions of its agents, but it had a transformer to draw attention to a subset of the inputs
[–] maximur 7y ago ↗ It would be nice to get an in-depth overview of the techniques used behind AlphaStar...
[–] rafaiero1 7y ago ↗ DeepMind reduced the problem to search using the two Deep Neural Networks. MCTS is an old technique but it clearly worked here
4 comments
[ 23.8 ms ] story [ 1441 ms ] thread