HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism
This addresses instability issues in cooperative multi-agent systems, offering a domain-agnostic solution, though it appears incremental as an extension of hierarchical reinforcement learning methods.
The paper tackles the challenge of instability in hierarchical multi-agent reinforcement learning by proposing HAVEN, a value decomposition framework with a dual coordination mechanism, which outperforms other algorithms on decentralized partially observable Markov decision process domains.
Recently, some challenging tasks in multi-agent systems have been solved by some hierarchical reinforcement learning methods. Inspired by the intra-level and inter-level coordination in the human nervous system, we propose a novel value decomposition framework HAVEN based on hierarchical reinforcement learning for fully cooperative multi-agent problems. To address the instability arising from the concurrent optimization of policies between various levels and agents, we introduce the dual coordination mechanism of inter-level and inter-agent strategies by designing reward functions in a two-level hierarchy. HAVEN does not require domain knowledge and pre-training, and can be applied to any value decomposition variant. Our method achieves desirable results on different decentralized partially observable Markov decision process domains and outperforms other popular multi-agent hierarchical reinforcement learning algorithms.