Kaixhin / Kaixhin/Atari

Implement Retrace(λ)

Open
#37 0 comments 3 reactions 0 assignees View on GitHub
enhancement
Dominant language
Lua
Stars
263
Forks
72
PR merge metrics
No merged PRs in 30d

Description

[Safe and efficient off-policy reinforcement learning](https://arxiv.org/abs/1606.02647) implements this new algorithm with experience replay, but actually uses asynchrononous agents with experience replay for testing (the combination was going to happen soon enough). Which means that this repo is a unique position of having both components already implemented.

Contributor guide

Open the contributing guide

Research direction

Read the linked Retrace paper and inspect the repository’s existing experience-replay and asynchronous-agent components. No files, tests, or entry points are named; done should mean the Retrace algorithm is integrated with those components and its behavior is validated.

Written by the indexing model from the issue text.

Assessment

Tech stack
lua
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.