Emergent Cooperation Through Mutual Information Maximization

Abstract

With artificial intelligence systems becoming ubiquitous in our society, its designers will soon have to start to consider its social dimension, as many of these systems will have to interact among them to work efficiently. With this in mind, we propose a decentralized deep reinforcement learning algorithm for the design of cooperative multi-agent systems. The algorithm is based on the hypothesis that highly correlated actions are a feature of cooperative systems, and hence, we propose the insertion of an auxiliary objective of maximization of the mutual information between the actions of agents in the learning problem. Our system is applied to a social dilemma, a problem whose optimal solution requires that agents cooperate to maximize a macroscopic performance function despite the divergent individual objectives of each agent. By comparing the performance of the proposed system to a system without the auxiliary objective, we conclude that the maximization of mutual information among

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keycuervo2020emergent

Related papers

• Cooperative Artificial Intelligence (2022)0.00
• Emergent Cooperation Under Uncertain Incentive Alignment (2024)2.26
• Iterated Reasoning With Mutual Information In Cooperative And Byzantine Decentralized Teaming (2022)0.00
• Social Influence As Intrinsic Motivation For Multi-agent Deep Reinforcement Learning (2018)0.00
• Evolving Intrinsic Motivations For Altruistic Behavior (2018)2.26
• Cooperation Dynamics In Multi-agent Systems: Exploring Game-theoretic Scenarios With Mean-field Equilibria (2023)0.00
• Improved Cooperation By Balancing Exploration And Exploitation In Intertemporal Social Dilemma Tasks (2021)0.00
• Understanding The World To Solve Social Dilemmas Using Multi-agent Reinforcement Learning (2023)0.00