On Diagnostics for Understanding Agent Training Behaviour in Cooperative MARL

Wiem Khlifi, Siddarth Singh, Omayma Mahjoub, Ruan John de Kock, Abidine Vall, Rihab Gorsane, Arnu Pretorius

Confirmation: I accept the constraint that If the paper will be accepted at least one of the authors will attend the workshop and present the work

Keywords: XAI, Multi-Agent Reinforcement Learning, Explainable AI

TL;DR: This work explores the application of XAI tools to gain insights into the behavior of agents in cooperative multi-agent reinforcement learning (MARL) systems.

Abstract: Cooperative multi-agent reinforcement learning (MARL) has made substantial strides in addressing the distributed decision-making challenges. However, as multi-agent systems grow in complexity, gaining a comprehensive understanding of their behaviour becomes increasingly challenging. Conventionally, tracking team rewards over time has served as a pragmatic measure to gauge the effectiveness of agents in learning optimal policies. Nevertheless, we argue that relying solely on the empirical returns may obscure crucial insights into agent behaviour. In this paper, we explore the application of explainable AI (XAI) tools to gain profound insights into agent behaviour. We employ these diagnostics within the context of Level-Based Foraging and Multi-Robot Warehouse environments and apply them to a diverse array of MARL algorithms.

Submission Type: Short Paper

Submission Number: 5