#artificial intelligence
Jun 2026
Learning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning
Preference Coordinated Multi-agent Policy Optimization (PCMA), which learns coordinated agent-specific preferences to enable complementary trade-offs among agents to improve both performance and trade-off coordination is proposed.
Peng-Xin Wang, Li-Hao Guo, Yimei Xie et al.
· arXiv.org · 0 citations