Timezone: »

 
Poster
Multi-Agent Determinantal Q-Learning
Yaodong Yang · Ying Wen · Jun Wang · Liheng Chen · Kun Shao · David Mguni · Weinan Zhang

Thu Jul 16 02:00 PM -- 02:45 PM & Fri Jul 17 03:00 AM -- 03:45 AM (PDT) @
in Poster Session 47 »

Centralized training with decentralized execution has become an important paradigm in multi-agent learning. Though practical, current methods rely on restrictive assumptions to decompose the centralized value function across agents for execution. In this paper, we eliminate this restriction by proposing multi-agent determinantal Q-learning. Our method is established on Q-DPP, a novel extension of determinantal point process (DPP) to multi-agent setting. Q-DPP promotes agents to acquire diverse behavioral models; this allows a natural factorization of the joint Q-functions with no need for \emph{a priori} structural constraints on the value function or special network architectures. We demonstrate that Q-DPP generalizes major solutions including VDN, QMIX, and QTRAN on decentralizable cooperative tasks. To efficiently draw samples from Q-DPP, we develop a linear-time sampler with theoretical approximation guarantee. Our sampler also benefits exploration by coordinating agents to cover orthogonal directions in the state space during training. We evaluate our algorithm on multiple cooperative benchmarks; its effectiveness has been demonstrated when compared with the state-of-the-art.

Keywords: Multiagent Learning · Reinforcement Learning · Planning, Control, and Multiagent Learning

Author Information

Yaodong Yang (Huawei UK)
Ying Wen (UCL)
Jun Wang (UCL)
Liheng Chen (Shanghai Jiao Tong University)
Kun Shao (Huawei Noah's Ark Lab)
David Mguni (Noah's Ark Laboratory, Huawei)
Weinan Zhang (Shanghai Jiao Tong University)

More from the Same Authors