On The Hardness of Reinforcement Learning With Value-Function Approximation

About this video

Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

Hardness of reinforcement learning with value-function approximation. Theoretical analysis of RL complexity and convergence challenges.

A 77-minute video from Microsoft Research: “On The Hardness of Reinforcement Learning With Value-Function Approximation”.

Video by Microsoft Research, played through YouTube's embedded player.