Kaixhin/Atari

Implement Pop-Art

Open

#6 opened on Apr 13, 2016

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Lua (72 forks)github user discovery
enhancementhelp wanted

Repository metrics

Stars
 (263 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

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

Contributor guide

Research direction
Read the Pop Art paper and understand how to adapt the existing DQN implementation to incorporate adaptive output scaling.
Tech stack
lua
Domain
machine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Needs investigation
Prerequisites
LuaReinforcement learning
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
20