AI Paper Atlas

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

Hierarchical Mean-Field Deep Reinforcement Learning for Large-Scale Multiagent Systems

Chao Yu

AAAI 2023 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Coordination graphs · 6 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 hierarchical intra-group and inter-group coordinationHMF · Spread and Pursuit Evasionaverage reward per learning episodeImproved
Use hierarchical intra-group and inter-group coordinationHMF · Battleaverage reward per learning episodeImproved
Use hierarchical intra-group and inter-group coordinationHMF · Bar Gameaverage reward per learning episode: 0.6Improved
Add Information and Policy Consistency dynamic groupingHMF · Spread, Pursuit Evasion, and Battleaverage reward per learning episodeImproved
Use an intermediate number of groups rather than fewer or more groups (ablation)HMF · Pursuit Evasionaverage reward per learning episodeMixed
Use two groups rather than three groups (ablation)HMF · Spreadaverage reward per learning episodeImproved
Increase the number of supervisors as the agent population grows (ablation)HMF · Battleaverage reward per learning episodeImproved
Add the regularization constraint (ablation)HMF · The evaluated taskslearning performanceImproved
Add top-level learning across group mean-field functions (ablation)HMF · The evaluated taskslearning efficiencyImproved
Vary the number of groups (ablation)HMF · Bar Gameaverage reward per learning episodeNo clear effect

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