Research map / Multi-agent systems and games / Cooperative multi-agent RL
Hierarchical Mean-Field Deep Reinforcement Learning for Large-Scale Multiagent Systems
Chao Yu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use hierarchical intra-group and inter-group coordination | HMF · Spread and Pursuit Evasion | average reward per learning episode | Improved |
| Use hierarchical intra-group and inter-group coordination | HMF · Battle | average reward per learning episode | Improved |
| Use hierarchical intra-group and inter-group coordination | HMF · Bar Game | average reward per learning episode: 0.6 | Improved |
| Add Information and Policy Consistency dynamic grouping | HMF · Spread, Pursuit Evasion, and Battle | average reward per learning episode | Improved |
| Use an intermediate number of groups rather than fewer or more groups (ablation) | HMF · Pursuit Evasion | average reward per learning episode | Mixed |
| Use two groups rather than three groups (ablation) | HMF · Spread | average reward per learning episode | Improved |
| Increase the number of supervisors as the agent population grows (ablation) | HMF · Battle | average reward per learning episode | Improved |
| Add the regularization constraint (ablation) | HMF · The evaluated tasks | learning performance | Improved |
| Add top-level learning across group mean-field functions (ablation) | HMF · The evaluated tasks | learning efficiency | Improved |
| Vary the number of groups (ablation) | HMF · Bar Game | average reward per learning episode | No clear effect |
Closest papers by meaning
- Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics (NeurIPS 2025 · similarity 0.89)
- Major-Minor Mean Field Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.89)
- Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
- Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior (ICLR 2024 · similarity 0.87)
- Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games (NeurIPS 2026 · similarity 0.86)
- Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximation (ICLR 2025 · similarity 0.86)
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.
