Research map / Multi-agent systems and games / Cooperative multi-agent RL
Learning Multi-Agent Communication through Structured Attentive Reasoning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 SARNet communication instead of TarMAC | multi-agent RL · Cooperative Navigation N=L=10 | reward: -21.71 -> -14.73 | Helped |
| use SARNet instead of TarMAC | multi-agent RL · Cooperative Navigation N=L=6 | reward: -17.16 -> -12.39 | Helped |
| use SARNet instead of non-communicating MADDPG | multi-agent RL · Cooperative Navigation N=L=6 | reward: -13.12 -> -12.39 | Helped |
| use SARNet instead of TarMAC | predators · Predator-Prey 6 vs 2 | # captures: 16.18 -> 17.51 | Helped |
| use SARNet instead of TarMAC | predators · Predator-Prey 12 vs 4 | # captures: 23.33 -> 25.34 | Helped |
| use SARNet instead of TarMAC/CommNet with 6 agents | traffic agents · Traffic Junction N=6 | success rate (%): 76.35 -> 74.27 | No clear effect |
| use SARNet instead of TarMAC with more agents | traffic agents · Traffic Junction N=20 | success rate (%): 59.36 -> 65.65 | Helped |
| use SARNet instead of TarMAC | traffic agents · Traffic Junction N=10 | success rate (%): 85.94 -> 94.81 | Helped |
Closest papers by meaning
- Learning Attentional Communication for Multi-Agent Cooperation (NeurIPS 2018 · similarity 0.92)
- Learning Multi-Agent Communication from Graph Modeling Perspective (ICLR 2024 · similarity 0.89)
- Multi-Agent Reinforcement Learning with Communication-Constrained Priors (NeurIPS 2025 · similarity 0.89)
- Learning Multi-Agent Communication with Contrastive Learning (ICLR 2024 · similarity 0.88)
- Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation (AAAI 2025 · similarity 0.88)
- Benefits and Limitations of Communication in Multi-Agent Reasoning (ICLR 2026 · similarity 0.88)
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.