A repository to reproduce the experiments of the MA-POCA paper

Перейти к файлу

Vincent-Pierre BERGES 885144ee25 Merge pull request #10 from Unity-Technologies/develop-rename-license add -md to license		2021-10-06 11:11:09 -07:00
ma-poca	Merge branch 'main' into develop-add-readme	2021-09-22 09:42:47 -07:00
.gitignore	Moving ma-poca to folder	2021-09-15 14:47:59 -07:00
CONTRIBUTING.md	adding a contributing.md file	2021-09-27 09:27:47 -07:00
LICENSE.md	add -md to license	2021-10-06 11:10:42 -07:00
README.md	initial documentation commit	2021-09-22 09:33:17 -07:00
catalog-info.yaml	Update owner field for Backstage Catalog	2021-09-16 15:53:42 +00:00

README.md

papers-ml-agents

This repository is meant to offer a way to reproduce the experiments of some of the papers Unity published using ML-Agents.

MA-POCA

Multi-Agent POsthumous Credit Assignment (MA-POCA) is a multi-agent learning algorithm that can gracefully deal with spawning and despawning agents without the use of absorbing states. See here for more information.