Improving Global Parameter-sharing in Physically Heterogeneous Multi-agent Reinforcement Learning with Unified Action Space

TL;DR

This paper introduces the Unified Action Space (UAS) to improve parameter-sharing among heterogeneous agents in multi-agent reinforcement learning, enhancing cooperation without excessive computational costs.

Contribution

The paper proposes UAS and a Cross-Group Inverse loss to better handle action semantics, enabling effective parameter-sharing in heterogeneous multi-agent systems.

Findings

UAS improves cooperation in heterogeneous MAS

U-QMIX and U-MAPPO outperform state-of-the-art methods

Effective in SMAC environment

Abstract

In a multi-agent system (MAS), action semantics indicates the different influences of agents' actions toward other entities, and can be used to divide agents into groups in a physically heterogeneous MAS. Previous multi-agent reinforcement learning (MARL) algorithms apply global parameter-sharing across different types of heterogeneous agents without careful discrimination of different action semantics. This common implementation decreases the cooperation and coordination between agents in complex situations. However, fully independent agent parameters dramatically increase the computational cost and training difficulty. In order to benefit from the usage of different action semantics while also maintaining a proper parameter-sharing structure, we introduce the Unified Action Space (UAS) to fulfill the requirement. The UAS is the union set of all agent actions with different semantics. All agents first calculate their unified representation in the UAS, and then generate their heterogeneous action policies using different available-action-masks. To further improve the training of extra UAS parameters, we introduce a Cross-Group Inverse (CGI) loss to predict other groups' agent policies with the trajectory information. As a universal method for solving the physically heterogeneous MARL problem, we implement the UAS adding to both value-based and policy-based MARL algorithms, and propose two practical algorithms: U-QMIX and U-MAPPO. Experimental results in the SMAC environment prove the effectiveness of both U-QMIX and U-MAPPO compared with several state-of-the-art MARL methods.