Skip to content

Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions

About this video

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

Explains Reinforcement Learning Upside Down approach mapping observations to actions without explicit reward prediction. Technical paper walkthrough of alternative RL framework design.

Video by Yannic Kilcher, played through YouTube's embedded player.

Part of Reinforcement Learning