Learning Independently from Causality in Multi-Agent Environments
This work addresses the lazy agent pathology in MARL, which is a specific issue for decentralized multi-agent systems, and is incremental by applying causality concepts to an existing problem.
The paper tackles the lazy agent problem in multi-agent reinforcement learning by analyzing causal relationships between individual observations and team rewards, showing that this approach improves team performance and fosters more intelligent individual behaviors.
Multi-Agent Reinforcement Learning (MARL) comprises an area of growing interest in the field of machine learning. Despite notable advances, there are still problems that require investigation. The lazy agent pathology is a famous problem in MARL that denotes the event when some of the agents in a MARL team do not contribute to the common goal, letting the teammates do all the work. In this work, we aim to investigate this problem from a causality-based perspective. We intend to create the bridge between the fields of MARL and causality and argue about the usefulness of this link. We study a fully decentralised MARL setup where agents need to learn cooperation strategies and show that there is a causal relation between individual observations and the team reward. The experiments carried show how this relation can be used to improve independent agents in MARL, resulting not only on better performances as a team but also on the rise of more intelligent behaviours on individual agents.