TACTIC: Task-agnostic Contrastive Pre-training For Inter-agent Communication

Abstract

The "sight range dilemma" in cooperative Multi-Agent Reinforcement Learning (MARL) presents a significant challenge: limited observability hinders team coordination, while extensive sight ranges lead to distracted attention and reduced performance. While communication can potentially address this issue, existing methods often struggle to generalize across different sight ranges, limiting their effectiveness. We propose TACTIC, Task-Agnostic Contrastive pre-Training strategy Inter-Agent Communication. TACTIC is an adaptive communication mechanism that enhances agent coordination even when the sight range during execution is vastly different from that during training. The communication mechanism encodes messages and integrates them with local observations, generating representations grounded in the global state using contrastive learning. By learning to generate and interpret messages that capture important information about the whole environment, TACTIC enables agents to effectively "se

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyyu2025tactic

Related papers

• AC2C: Adaptively Controlled Two-hop Communication For Multi-agent Reinforcement Learning (2023)0.00
• Attention-guided Contrastive Role Representations For Multi-agent Reinforcement Learning (2023)3.64
• Tacit Learning With Adaptive Information Selection For Cooperative Multi-agent Reinforcement Learning (2024)0.00
• Multi-agent Continual Coordination Via Progressive Task Contextualization (2023)5.24
• From Explicit Communication To Tacit Cooperation:a Novel Paradigm For Cooperative MARL (2023)3.58
• Context-aware Communication For Multi-agent Reinforcement Learning (2023)3.14
• Communicating Plans, Not Percepts: Scalable Multi-agent Coordination With Embodied World Models (2025)0.00
• Cheap Talk Discovery And Utilization In Multi-agent Reinforcement Learning (2023)0.00