AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

Heterogeneous-Agent Reinforcement Learning

Yifan Zhong, Jakub Grudzien Kuba, Xidong Feng, Siyi Hu, Jiaming Ji, Yaodong Yang

JMLR 2024 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Cooperative MARL algorithms · 45 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use HAPPO sequential update with non-shared parameters instead of MAPPO with parameter sharingHAPPO vs MAPPO · MAMuJoCo (5 tasks)average episode returnImproved
use HAPPO instead of MAPPO on a many-heterogeneous-agent taskHAPPO · MAMuJoCo 17-agent Humanoidaverage episode returnImproved
use HATD3 instead of MATD3 and HADDPGHATD3 · MAMuJoCo (5 tasks)average episode returnImproved
use HAPPO instead of MAPPO on simple MPE tasksHAPPO · MPE (continuous and discrete)average episode returnNo clear effect
use HAA2C (no trust region constraint) on continuous MPE tasksHAA2C · MPE (continuous)average episode returnHurt
use off-policy HARL methods instead of on-policy onesHADDPG, HATD3 · MPEsample efficiencyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy