Episode 19: Minqi Jiang, UCL, on environment and curriculum design for general RL agents
Generally Intelligent
00:00
How to Find the Most Challenging Levels in the Environment
E sot ac cell work basely build on those concepts. We basily use this like minimac regret base curriculum, essentially robust plr. But the insight there is that robust pelar ultimately its curating. It's trying to find needles in the haystack that are the most challenging levels. And if you think about it, that becomes a harder and harder problem as the policy of ves and gets better.
Transcript
Play full episode
