Sai Krishna Gottipati
TalkRL: The Reinforcement Learning Podcast
00:00
Can Agents Collaborate?
There is a very limited number of hints that you could get. This acts like a good bench mack for teaching agents to collaborate with each other, or having bringing humans in the lup and teaching agents to co operate or collaborate with humans. But given the these limited communication capabilities that we deem are perffectly safe, can this, can they learn too? Can they learn useful co operative behaviors? That's a very good challenge to have. It also seems to me a bit artificial, in the sense that, a this game is only fun because you can't say, hey, si, you're carrying a yellow two and a red three. I'm not allowed to say that to
Play episode from 36:38
Transcript
