Danijar Hafner 2
TalkRL: The Reinforcement Learning Podcast
The Progression From Planet to Dreamer
The project started with planet, the deep planning network. And then there was Dreamer 1, 2, and 3. The vision hasn't changed along the way, just the algorithmic details to make it work better and better. I see from the paper exceeds Impala performance while using 130 times fewer environment steps like that is a really big difference. It's easy for people to forget how incremental and gradual the progress is over many years.
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.
