Kaixhin/Atari

Implement Pop-Art

Open

#6 opened on 2016年4月13日

GitHub で見る
 (0 comments) (0 reactions) (0 assignees)Lua (72 forks)github user discovery
enhancementhelp wanted

Repository metrics

Stars
 (263 stars)
PR merge metrics
 (30d に merged PR はありません)

説明

Learning functions across many orders of magnitudes introduces Preserving Outputs Precisely, while Adaptively Rescaling Targets (Pop-Art). In summary it normalises outputs across orders of magnitudes and gets rid of the clipping (i.e. counting) rewards heuristic for Atari games. The normalisation is also better for non-stationary problems, i.e., any decent real world problem.

The below is a picture of extra notes from the authors, next to their poster at NIPS 2016: img_20161207_190428

コントリビューターガイド