Lecture by Sergey Levine about progress on real-world deep RL. Covers these papers:
A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning: [ Ссылка ]
Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion: [ Ссылка ]
Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention: [ Ссылка ]
REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation: [ Ссылка ]
FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing: [ Ссылка ]
Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions: [ Ссылка ]
Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators: [ Ссылка ]
Ещё видео!