Research map / Multi-agent systems and games / Cooperative multi-agent RL
Efficient Multi-agent Communication via Self-supervised Information Aggregation
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 |
|---|---|---|---|
| add MASIA message aggregation to VDN, QMIX and QPLEX | value-decomposition baselines · SMAC 1o10b_vs_1r | average test win rate | Helped |
| narrow agents' sight range from 9 to 6 and 3 (ablation) | MASIA · SMAC 1o10b_vs_1r | median test win rate | No clear effect |
| replace learned messages with MASIA aggregation over no communication (QMIX) | QMIX · Hallway | median test win rate | Helped |
| use targeted or minimized messages (TarMAC, NDQ, TMC) instead of aggregation | communication baselines · Hallway | median test win rate | Hurt |
| add MASIA communication on top of QMIX | QMIX · LBF | median test win rate | No clear effect |
Closest papers by meaning
- Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation (AAAI 2025 · similarity 0.90)
- Learning Efficient and Robust Multi-Agent Communication via Graph Information Bottleneck (AAAI 2024 · similarity 0.89)
- Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems (AAAI 2025 · similarity 0.88)
- Multi-Agent Reinforcement Learning with Communication-Constrained Priors (NeurIPS 2025 · similarity 0.88)
- PMAC: Personalized Multi-Agent Communication (AAAI 2024 · similarity 0.88)
- Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning (ICLR 2025 · 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.
