Learning Multiagent Coordination In The Absence Of Communication Channels

Abstract

In this work, we develop a reinforcement learning protocol for a multiagent coordination task in a discrete state and action space: an iterated prisoner's dilemma game extended into a team based, winner-take all tournament, which forces the agents to collude in order to maximize their reward. By disallowing extra communication channels, the agents are forced to embed their coordination strategy into their actions in the prisoner's dilemma game. We develop a representation of the iterated prisoners dilemma that makes it amenable to Q-learning. We find that the reinforcement learning strategy is able to consistently train agents that can win the winner take all iterated prisoners dilemma tournament. By using a game with discrete state and action space, we are able to better analyze and understand both the dynamics and the communication protocols that are established between the agents. We find that the agents adapt a number of interesting behaviors, such as the formation of benevolen

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygoodman2018learning

Related papers

• Resolving Implicit Coordination In Multi-agent Deep Reinforcement Learning With Deep Q-networks & Game Theory (2020)0.00
• Coordination-driven Learning In Multi-agent Problem Spaces (2018)0.00
• Towards Cooperation In Sequential Prisoner's Dilemmas: A Deep Multiagent Reinforcement Learning Approach (2018)0.00
• Cooperation Dynamics In Multi-agent Systems: Exploring Game-theoretic Scenarios With Mean-field Equilibria (2023)0.00
• Multi-agent Coordination In Adversarial Environments Through Signal Mediated Strategies (2021)2.26
• Mixed Cooperative-competitive Communication Using Multi-agent Reinforcement Learning (2021)5.84
• Learning Practical Communication Strategies In Cooperative Multi-agent Reinforcement Learning (2022)0.00
• Signal Instructed Coordination In Cooperative Multi-agent Reinforcement Learning (2019)4.52