GHQ: Grouped Hybrid Q Learning for Heterogeneous Cooperative Multi-agent Reinforcement Learning
It addresses the harder problem of heterogeneous scenarios in MARL for applications like gaming and robotics, but it is incremental as it builds on existing methods like Q-learning and grouping.
The paper tackles cooperative heterogeneous multi-agent reinforcement learning in Starcraft Multi-Agent Challenges by proposing GHQ, which groups agents and uses a hybrid structure with inter-group mutual information, achieving superior performance on new and original maps compared to state-of-the-art algorithms.
Previous deep multi-agent reinforcement learning (MARL) algorithms have achieved impressive results, typically in homogeneous scenarios. However, heterogeneous scenarios are also very common and usually harder to solve. In this paper, we mainly discuss cooperative heterogeneous MARL problems in Starcraft Multi-Agent Challenges (SMAC) environment. We firstly define and describe the heterogeneous problems in SMAC. In order to comprehensively reveal and study the problem, we make new maps added to the original SMAC maps. We find that baseline algorithms fail to perform well in those heterogeneous maps. To address this issue, we propose the Grouped Individual-Global-Max Consistency (GIGM) and a novel MARL algorithm, Grouped Hybrid Q Learning (GHQ). GHQ separates agents into several groups and keeps individual parameters for each group, along with a novel hybrid structure for factorization. To enhance coordination between groups, we maximize the Inter-group Mutual Information (IGMI) between groups' trajectories. Experiments on original and new heterogeneous maps show the fabulous performance of GHQ compared to other state-of-the-art algorithms.