Learning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning
Cooperative multi-objective multi-agent reinforcement learning (MOMARL) models team decision making under multiple, potentially conflicting objectives. In this setting, conflicts arise not only across objectives but also across agents with different observations, roles, and contributions. We propose Preference Coordinated Multi-agent Policy Optimization (PCMA), which learns coordinated agent-specific preferences to enable complementary trade-offs among agents. Theoretically, we formulate cooperative MOMARL as a team-optimal game and show that, under suitable conditions, preference diversity can induce team improvement through a first-order improvement decomposition. Experiments on multiple cooperative MOMA environments and a practical traffic-control scenario show that PCMA improves both performance and trade-off coordination.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-agent Reinforcement LearningDecision MakingSimilar Papers 제목 키워드 기반
Coordinated Proximal Policy Optimization
We present Coordinated Proximal Policy Optimization (CoPPO), an algorithm that extends the original Proximal Policy Optimization (PPO) to the multi-agent setting. The key idea lies in the coordinated adaptation of step s…
StarcraftStarcraft IIAgentRec: Next-Generation LLM-Powered Multi-Agent Collaborative Recommendation with Adaptive Intelligence
Interactive conversational recommender systems have gained significant attention for their ability to capture user preferences through natural language interactions. However, existing approaches face substantial challeng…
Co-Optimization of Environment and Policies for Decentralized Multi-Agent Navigation
This work views the multi-agent system and its surrounding environment as a co-evolving system, where the behavior of one affects the other. The goal is to take both agent actions and environment configurations as decisi…
Coordination-driven learning in multi-agent problem spaces
We discuss the role of coordination as a direct learning objective in multi-agent reinforcement learning (MARL) domains. To this end, we present a novel means of quantifying coordination in multi-agent systems, and discu…
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization
Software engineering presents complex, multi-step challenges for Large Language Models (LLMs), requiring reasoning over large codebases and coordinated tool use. The difficulty of these tasks is exemplified by benchmarks…