Multi-agent Coordination In Adversarial Environments Through Signal Mediated Strategies

Abstract

Many real-world scenarios involve teams of agents that have to coordinate their actions to reach a shared goal. We focus on the setting in which a team of agents faces an opponent in a zero-sum, imperfect-information game. Team members can coordinate their strategies before the beginning of the game, but are unable to communicate during the playing phase of the game. This is the case, for example, in Bridge, collusion in poker, and collusion in bidding. In this setting, model-free RL methods are oftentimes unable to capture coordination because agents' policies are executed in a decentralized fashion. Our first contribution is a game-theoretic centralized training regimen to effectively perform trajectory sampling so as to foster team coordination. When team members can observe each other actions, we show that this approach provably yields equilibrium strategies. Then, we introduce a signaling-based framework to represent team coordinated strategies given a buffer of past experiences.

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keycacciamani2021multi

Related papers

• Signal Instructed Coordination In Cooperative Multi-agent Reinforcement Learning (2019)4.52
• Learning Multiagent Coordination In The Absence Of Communication Channels (2018)0.00
• Coordination-driven Learning In Multi-agent Problem Spaces (2018)0.00
• Emergent Coordination Through Competition (2019)0.00
• Multi-agent Curricula And Emergent Implicit Signaling (2021)0.00
• Multi-agent Actor-critic For Mixed Cooperative-competitive Environments (2017)0.00
• GCS: Graph-based Coordination Strategy For Multi-agent Reinforcement Learning (2022)0.00
• Training Generalizable Collaborative Agents Via Strategic Risk Aversion (2026)0.00