Counterfactual Multi-agent Reinforcement Learning With Graph Convolution Communication

Abstract

We consider a fully cooperative multi-agent system where agents cooperate to maximize a system's utility in a partial-observable environment. We propose that multi-agent systems must have the ability to (1) communicate and understand the inter-plays between agents and (2) correctly distribute rewards based on an individual agent's contribution. In contrast, most work in this setting considers only one of the above abilities. In this study, we develop an architecture that allows for communication among agents and tailors the system's reward for each individual agent. Our architecture represents agent communication through graph convolution and applies an existing credit assignment structure, counterfactual multi-agent policy gradient (COMA), to assist agents to learn communication by back-propagation. The flexibility of the graph structure enables our method to be applicable to a variety of multi-agent systems, e.g. dynamic systems that consist of varying numbers of agents and static sy

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysu2020counterfactual

Related papers

• Counterfactual Multi-agent Policy Gradients (2017)0.00
• Universally Expressive Communication In Multi-agent Reinforcement Learning (2022)0.00
• Asynchronous Cooperative Multi-agent Reinforcement Learning With Limited Communication (2025)0.00
• A Survey Of Multi-agent Deep Reinforcement Learning With Graph Neural Network-based Communication (2026)0.00
• Cooperative Multi-agent Reinforcement Learning With Hypergraph Convolution (2021)5.84
• Multi-agent Reinforcement Learning With Communication-constrained Priors (2025)0.00
• Learning Practical Communication Strategies In Cooperative Multi-agent Reinforcement Learning (2022)0.00
• Graph Exploration For Effective Multi-agent Q-learning (2023)5.24