Theory Of Mind As Intrinsic Motivation For Multi-agent Reinforcement Learning

Abstract

The ability to model the mental states of others is crucial to human social intelligence, and can offer similar benefits to artificial agents with respect to the social dynamics induced in multi-agent settings. We present a method of grounding semantically meaningful, human-interpretable beliefs within policies modeled by deep networks. We then consider the task of 2nd-order belief prediction. We propose that ability of each agent to predict the beliefs of the other agents can be used as an intrinsic reward signal for multi-agent reinforcement learning. Finally, we present preliminary empirical results in a mixed cooperative-competitive environment.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyoguntola2023theory

Related papers

• Learning Human Rewards By Inferring Their Latent Intelligence Levels In Multi-agent Games: A Theory-of-mind Approach With Application To Driving Data (2021)0.00
• Social Influence As Intrinsic Motivation For Multi-agent Deep Reinforcement Learning (2018)0.00
• Probabilistic Recursive Reasoning For Multi-agent Reinforcement Learning (2019)0.00
• Competitive Multi-agent Deep Reinforcement Learning With Counterfactual Thinking (2019)7.16
• Innate-values-driven Reinforcement Learning Based Cooperative Multi-agent Cognitive Modeling (2024)0.00
• Belief States For Cooperative Multi-agent Reinforcement Learning Under Partial Observability (2025)0.00
• Embedded Universal Predictive Intelligence: A Coherent Framework For Multi-agent Learning (2025)0.00
• Metamind: General And Cognitive World Models In Multi-agent Systems By Meta-theory Of Mind (2026)0.00