Prioritized League Reinforcement Learning For Large-scale Heterogeneous Multiagent Systems

Abstract

Large-scale heterogeneous multiagent systems feature various realistic factors in the real world, such as agents with diverse abilities and overall system cost. In comparison to homogeneous systems, heterogeneous systems offer significant practical advantages. Nonetheless, they also present challenges for multiagent reinforcement learning, including addressing the non-stationary problem and managing an imbalanced number of agents with different types. We propose a Prioritized Heterogeneous League Reinforcement Learning (PHLRL) method to address large-scale heterogeneous cooperation problems. PHLRL maintains a record of various policies that agents have explored during their training and establishes a heterogeneous league consisting of diverse policies to aid in future policy optimization. Furthermore, we design a prioritized policy gradient approach to compensate for the gap caused by differences in the number of different types of agents. Next, we use Unreal Engine to design a large-s

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfu2024prioritized

Related papers

• Learning Heterogeneous Agent Cooperation Via Multiagent League Training (2022)7.16
• End-to-end Optimization Of Llm-driven Multi-agent Search Systems Via Heterogeneous-group-based Reinforcement Learning (2025)0.00
• Heterogeneous Multi-agent Reinforcement Learning For Zero-shot Scalable Collaboration (2024)6.34
• GHQ: Grouped Hybrid Q Learning For Heterogeneous Cooperative Multi-agent Reinforcement Learning (2023)6.34
• Heterogeneous-agent Reinforcement Learning (2023)0.00
• Pool: Pheromone-inspired Communication Framework Forlarge Scale Multi-agent Reinforcement Learning (2022)5.24
• Heterogeneous Multi-robot Reinforcement Learning (2023)6.77
• Evolution Of Societies Via Reinforcement Learning (2024)0.00