Research map / Multi-agent systems and games / Cooperative multi-agent RL
Exploiting Geometric Structures for Modeling Multi-Agent Behaviors: A New Thinking
Bohao Qu, Xiaofeng Cao, Bing Li, Menglin Zhang, Tuan-Anh Vu, Di Lin, Qing Guo
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 |
|---|---|---|---|
| add hyperbolic (Poincare ball) agent representations from HMAR to PPO instead of Euclidean AMF | PPO · Overcooked (5 layouts) | mean episode reward | Improved |
| add HMAR embeddings instead of recurrent-encoder LIAM | PPO · Overcooked (5 layouts) | mean episode reward | Improved |
| add HMAR opponent embeddings to PPO | PPO · Pommerman win rate vs naive PPO | win rate | Improved |
| add HMAR embeddings to PPO in early training | PPO · Pommerman early training | win rate | No clear effect |
| use HMAR-PPO against other embedding methods head to head after 1000 iterations | LIAM/AMF/CARL/PPO · Pommerman adversarial matches | win rate | Improved |
| early-phase Cramped Room: HMAR lets one agent act while other idles | PPO · Overcooked Cramped Room | mean episode reward | Mixed |
Closest papers by meaning
- HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning (ICML 2025 · similarity 0.88)
- Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective (NeurIPS 2025 · similarity 0.86)
- HyperMARL: Adaptive Hypernetworks for Multi-Agent RL (NeurIPS 2025 · similarity 0.86)
- Mental-Models for Multi-Agent Systems (NeurIPS 2026 · similarity 0.86)
- Learning Joint Behaviors with Large Variations (AAAI 2025 · similarity 0.86)
- Detecting Influence Structures in Multi-Agent Reinforcement Learning (ICML 2024 · 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.
