AI Paper Atlas

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

Learning to Simulate Self-driven Particles System with Coordinated Policy Optimization

Zhenghao Peng, Quanyi Li, Ka Ming Hui, Chunxiao Liu, Bolei Zhou

NeurIPS 2021 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping · 11 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 CoPO's local and global coordination instead of IPOtraffic MARL populations · Roundabout, Intersection, Tollgate, Bottleneck, and Parking Lotsuccess rate: 73.67 vs 70.81; 78.97 vs 60.47; 86.13 vs 82.90; 79.68 vs 72.43; 65.04 vs 61.05Improved
replace the learned LCF distribution with fixed N(0, 0.1²) (ablation)CoPO · Roundabout, Intersection, Tollgate, Bottleneck, and Parking Lotsuccess rate: 62.38 vs 73.67; 70.23 vs 78.97; 60.47 vs 86.13; 71.29 vs 79.68; 59.14 vs 65.04Hurt
replace CoPO with IPO maximizing global reward directly (ablation)CoPO · Roundabout, Intersection, Tollgate, Bottleneck, and Parking Lotsuccess rate: 0.00 { $\pm$ 0.00} on all five environmentsHurt
optimize neighborhood reward alone instead of balancing individual and neighborhood rewards (ablation)CoPO · Roundabout, Intersection, Tollgate, Bottleneck, and Parking Lotsuccess rate: 65.70 vs 73.67; 66.83 vs 78.97; 57.30 vs 86.13; 71.62 vs 79.68; 6.34 vs 65.04Hurt
add centralized critics to CoPO (ablation)CoPO · traffic environmentssuccess rateHurt
use neighborhood mean-field inputs rather than concatenated nearby-agent states in centralized critics (ablation)MFPO · Roundabouttraining stabilityImproved
add neighbors' actions alongside observations to centralized critics (ablation)centralized critic variants · Roundabouttraining stabilityImproved
train with a distributional LCF rather than one fixed social-orientation factorCoPO · traffic populations with heterogeneous IDM policiessuccess rate: IPO (25% IDM): 55.17; CoPO (25% IDM): 71.55; IPO (50% IDM): 52.14; CoPO (50% IDM): 63.34Improved

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