Sai Krishna Gottipati
TalkRL: The Reinforcement Learning Podcast
00:00
Is There an Alternative to Population Base Training?
Hannaby: I think te hanabios biscl kind of a simpler version of the game wer. We don't have any of those additional complexities of, letsirono vision or other kinds of representations. And the cour task here is just to learn the abilities of cooperation. You know, these types of games require a really good memory, true? Or tho that wat stratigo, actually,. Someone was saying that about stratigo, which is another game with a lot of partial information and e and the idea a. Is that a factor here? Or not not so muchso.
Play episode from 40:49
Transcript
