Achieving Equilibrium Under Utility Heterogeneity: An Agent-attention Framework For Multi-agent Multi-objective Reinforcement Learning

Abstract

Multi-agent multi-objective systems (MAMOS) have emerged as powerful frameworks for modelling complex decision-making problems across various real-world domains, such as robotic exploration, autonomous traffic management, and sensor network optimisation. MAMOS offers enhanced scalability and robustness through decentralised control and more accurately reflects inherent trade-offs between conflicting objectives. In MAMOS, each agent uses utility functions that map return vectors to scalar values. Existing MAMOS optimisation methods face challenges in handling heterogeneous objective and utility function settings, where training non-stationarity is intensified due to private utility functions and the associated policies. In this paper, we first theoretically prove that direct access to, or structured modeling of, global utility functions is necessary for the Bayesian Nash Equilibrium under decentralised execution constraints. To access the global utility functions while preserving the de

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2025achieving

Related papers

• Learning And Calibrating Heterogeneous Bounded Rational Market Behaviour With Multi-agent Reinforcement Learning (2024)0.00
• Equilibrium Selection For Multi-agent Reinforcement Learning: A Unified Framework (2024)0.00
• Utility-based Reinforcement Learning: Unifying Single-objective And Multi-objective Reinforcement Learning (2024)2.26
• Maximum Entropy Heterogeneous-agent Reinforcement Learning (2023)0.00
• Opponent Learning Awareness And Modelling In Multi-objective Normal Form Games (2020)7.16
• Efficient Model-based Multi-agent Reinforcement Learning Via Optimistic Equilibrium Computation (2022)0.00
• Addressing The Issue Of Stochastic Environments And Local Decision-making In Multi-objective Reinforcement Learning (2022)0.00
• Strategic Coordination For Evolving Multi-agent Systems: A Hierarchical Reinforcement And Collective Learning Approach (2025)0.00