AI Paper Atlas

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

Coordinated Proximal Policy Optimization

Zifan Wu, Chao Yu, Deheng Ye, Junge Zhang, haiyin piao, Hankz Hankui Zhuo

NeurIPS 2021 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Decentralized actor-critic MARL · 1 citations (OpenAlex)

Read the paper

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 CoPPO coordinated step-size adaptation instead of independent PPO updates (MAPPO)CoPPO · 4-agent 9-action penalty matrix gameaverage rewardImproved
remove the double clipping trick (ablation)CoPPO · penalty matrix gameaverage reward and gradient varianceHurt
vary inner clipping threshold among 0.05, 0.10, 0.15 (ablation)CoPPO · penalty matrix gameaverage rewardMixed
remove double clipping (ablation)CoPPO · SMAC (two maps)win rateHurt
replace weighted sum of local advantages with non-negative mixing network (Amix vs Asum) (ablation)CoPPO · SMAC (two maps)win rateNo clear effect
use CoPPO instead of MAPPO, COMA, DOP, QMIX, QTRANCoPPO · SMAC (3s5z, 10m_vs_11m, MMM2)win rateImproved
CoPPO instead of baselines across six matrix gamesCoPPO · six 4-agent matrix gamesaverage rewardImproved

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