Learning Explicit Credit Assignment for Multi-agent Joint Q-learning

29 Sep 2021  ·  Hangyu Mao, Jianye Hao, Dong Li, Jun Wang, Weixun Wang, Xiaotian Hao, Bin Wang, Kun Shao, Zhen Xiao, Wulong Liu ·

Multi-agent joint Q-learning based on Centralized Training with Decentralized Execution (CTDE) has become an effective technique for multi-agent cooperation. During centralized training, these methods are essentially addressing the multi-agent credit assignment problem. However, most of the existing methods \emph{implicitly} learn the credit assignment just by ensuring that the joint Q-value satisfies the Bellman optimality equation. In contrast, we formulate an \emph{explicit} credit assignment problem where each agent gives its suggestion about how to weight individual Q-values to explicitly maximize the joint Q-value, besides guaranteeing the Bellman optimality of the joint Q-value. In this way, we can conduct credit assignment among multiple agents and along the time horizon. Theoretically, we give a gradient ascent solution for this problem. Empirically, we instantiate the core idea with deep neural networks and propose Explicit Credit Assignment joint Q-learning (ECAQ) to facilitate multi-agent cooperation in complex problems. Extensive experiments justify that ECAQ achieves interpretable credit assignment and superior performance compared to several advanced baselines.

PDF Abstract
No code implementations yet. Submit your code now


  Add Datasets introduced or used in this paper

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.