MACTAS: Self-attention-based Inter-agent Communication In Multi-agent Reinforcement Learning With Action-value Function Decomposition

Abstract

Communication is essential for the collective execution of complex tasks by human agents, motivating interest in communication mechanisms for multi-agent reinforcement learning (MARL). However, existing communication protocols in MARL are often complex and non-differentiable. In this work, we introduce a self-attention-based communication method that exchanges information between the agents in MARL. Our proposed approach is fully differentiable, allowing agents to learn to generate messages in a reward-driven manner. The method can be seamlessly integrated with any action-value function decomposition algorithm and can be viewed as an orthogonal extension of such decompositions. Notably, it includes a fixed number of trainable parameters, independent of the number of agents, which makes it scalable to large systems. Experimental results on the SMACv2 benchmark demonstrate the effectiveness of our approach, which achieves state-of-the-art performance on a number of maps. makes it scalabl

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywojtala2025mactas

Related papers

• Context-aware Communication For Multi-agent Reinforcement Learning (2023)3.14
• AC2C: Adaptively Controlled Two-hop Communication For Multi-agent Reinforcement Learning (2023)0.00
• Modeling The Interaction Between Agents In Cooperative Multi-agent Reinforcement Learning (2021)0.00
• Transformer-based Value Function Decomposition For Cooperative Multi-agent Reinforcement Learning In Starcraft (2022)8.82
• Cheap Talk Discovery And Utilization In Multi-agent Reinforcement Learning (2023)0.00
• Communicating Plans, Not Percepts: Scalable Multi-agent Coordination With Embodied World Models (2025)0.00
• Decomposed Soft Actor-critic Method For Cooperative Multi-agent Reinforcement Learning (2021)0.00
• Learning Emergent Discrete Message Communication For Cooperative Reinforcement Learning (2021)5.24