Towards a Theory for Sample-efficient Reinforcement Learning with Rich Observations
Why it's on BrighterTube
Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceSample-efficient reinforcement learning with rich observations addresses data efficiency in deep RL. This teaches theoretical foundations and methods for learning from limited experience.
What you'll learn
A 54-minute video from Microsoft Research: “Towards a Theory for Sample-efficient Reinforcement Learning with Rich Observations”.
Video by Microsoft Research, played through YouTube's embedded player.