Slides: https://cwkx.github.io/data/teaching/dl-and-rl/rl-lecture10.pdf
Atari: https://www.youtube.com/playlist?list=PL34t13IwtOXUNliyyJtoamekLAbqhB9Il
Twitter: https://twitter.com/cwkx
Playlist: https://www.youtube.com/playlist?list=PLMsTLcO6ettgmyLVrcPvFLYi2Rs-R4JOE
Distributed and recurrent RL
- DQN characteristics
- recurrent replay in distributed RL
- R2D2 performance
Exploration vs exploitation
- approaches
Intrinsic rewards
- NGU: intrinsic motivation and curiosity
Latent recurrent imagination
- Dreamer and DreamerV2
AlphaStar and looking forward
- starting supervised
- self-play and league-play
#reinforcementlearning #selfplay #leagueplay #recurrentreplay #recurrentRL #atari #DQN #exploration #exploitation #r2d2 #ngu #alphastar #dreamer #openai
