Learning Reward Machines in Cooperative Multi-agent Tasks

This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) that combines cooperative task decomposition with the learning of Reward Machines (RMs) encoding the structure of the sub-tasks. The proposed method helps deal with the non-Markovian nature of the rewards in partially observable environments and improves the interpretability of the learnt policies required to complete a cooperative task. The RMs associated with the sub-tasks are learnt in a decentralised manner and then used to guide the behaviour of each agent in a team acting towards a common goal. By doing so, the complexity of a cooperative multi-agent problem is reduced, allowing for more effective learning. The results suggest that our approach is a promising direction for future research in cooperative MARL, especially in complex and partially observable environments.