Research map / Multi-agent systems and games / Cooperative multi-agent RL
Learning Efficient Multi-agent Communication: An Information Bottleneck Approach
Rundong Wang, Xu He, Runsheng Yu, Wei Qiu, Bo An, Zinovi Rabinovich
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 IMAC communication instead of the compared baseline methods | Predator-prey agents · Predator-prey | predator mean episode reward | Improved |
| Use IMAC communication instead of the compared baseline methods | Predator-prey agents · Predator-prey | prey mean episode reward | Mixed |
| Apply the same execution bandwidth constraint to IMAC rather than MADDPG with communication | Predator-prey agents · Predator-prey under limited bandwidth | mean episode reward | Improved |
| Use prior variance N(0,1) rather than a smaller or larger variance (ablation) | IMAC · Cooperative navigation | mean episode reward | Improved |
| Increase compression by using a smaller prior variance (ablation) | IMAC · Cooperative navigation | mean episode reward | Hurt |
| Increase prior variance above N(0,1) (ablation) | IMAC · Cooperative navigation | convergence speed | Hurt |
| Increase the information-bottleneck coefficient β (ablation) | IMAC · Cooperative navigation | mean episode reward | Hurt |
| Use QMIX with IMAC communication instead of QMIX with unlimited communication | QMIX · StarCraft II 3m and 8m | mean episode reward | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- TarMAC — TarMAC: Targeted Multi-Agent Communication (ICML 2019) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Multi-Agent Reinforcement Learning with Communication-Constrained Priors (NeurIPS 2025 · similarity 0.89)
- Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation (AAAI 2025 · similarity 0.89)
- Learning Efficient and Robust Multi-Agent Communication via Graph Information Bottleneck (AAAI 2024 · similarity 0.89)
- Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning (ICLR 2025 · similarity 0.88)
- Learning Multi-Agent Communication from Graph Modeling Perspective (ICLR 2024 · similarity 0.87)
- Learning Multi-Agent Communication with Contrastive Learning (ICLR 2024 · similarity 0.87)
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.
