HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism

• DOI: 10.1609/aaai.v37i10.26386
• Publication Date: 2023-06-27T17:59:03Z
• Authors: Zhiwei Xu; Yunpeng Bai; Bin Zhang; Dapeng Li; Guoliang Fan
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; 0202 electrical engineering, electronic engineering, information engineering; Computer Science - Multiagent Systems; 02 engineering and technology; Multiagent Systems (cs.MA); Machine Learning (cs.LG)

Recently, some challenging tasks in multi-agent systems have been solved by hierarchical reinforcement learning methods. Inspired the intra-level and inter-level coordination human nervous system, we propose a novel value decomposition framework HAVEN based on for fully cooperative problems. To address instability arising from concurrent optimization of policies between various levels agents, introduce dual mechanism inter-agent strategies designing reward functions two-level hierarchy. does not require domain knowledge pre-training, can be applied to any variant. Our method achieves desirable results different decentralized partially observable Markov decision process domains outperforms other popular algorithms.