Scalable Trust-Region Method for Deep Reinforcement Learning Using Kronecker-Factored Approximation
About this video
Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceScalable trust-region deep reinforcement learning teaches optimization methodology with Kronecker-factored approximation. Explains RL training efficiency.
A 73-minute video from Microsoft Research: “Scalable Trust-Region Method for Deep Reinforcement Learning Using Kronecker-Factored Approximation”.
Video by Microsoft Research, played through YouTube's embedded player.