
John Schulman
TalkRL: The Reinforcement Learning Podcast
What Are the Biggest Highlights in RL?
There's been a lot of work in RL since TRPO and PBO. TD3 and SAC seem like pretty solid value-based methods, he says. offline RL was also notable; we're training against that dataset.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.