Research map / Multi-agent systems and games / Cooperative multi-agent RL
In-Context Fully Decentralized Cooperative Multi-Agent Reinforcement Learning
Chao Li, Bingkun BAO, Yang Gao
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes an in-context learning approach for fully decentralized cooperative multi-agent RL that addresses non-stationarity and relative overgeneralization without access to other agents' actions.
Problem
Fully decentralized cooperative multi-agent RL, where each agent observes only states, its own actions, and shared rewards; this causes non-stationarity during value updates and relative overgeneralization during value estimation.
Approach
Uses in-context learning so that agents can infer other agents' behavior from context rather than relying on explicit access to their actions; the abstract is truncated so the precise mechanism is not stated.
Closest papers by meaning
- Multi-agent In-context Coordination via Decentralized Memory Retrieval (AAAI 2026 · similarity 0.91)
- Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning (ICML 2023 · similarity 0.90)
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.89)
- HyperMARL: Adaptive Hypernetworks for Multi-Agent RL (NeurIPS 2025 · similarity 0.88)
- Optimistic Value Instructors for Cooperative Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.88)
- Backpropagation Through Agents (AAAI 2024 · 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.
