Testing Reinforcement Learning Explainability Methods in a Multi-Agent Cooperative Environment

Abstract

The adoption of algorithms based on Artificial Intelligence (AI) has been rapidly increasing during the last years. However, some aspects of AI techniques are under heavy scrutiny. For instance, in many cases, it is not clear whether the decisions of an algorithm are well-informed and reliable. Having an answer to these concerns is crucial in many domains, such as those in were humans and intelligent agents must cooperate in a shared environment. In this paper, we introduce an application of an explainability method based on the creation of a Policy Graph (PG) based on discrete predicates that represent and explain a trained agent’s behaviour in a multi-agent cooperative environment. We also present a method to measure the similarity between the explanations obtained and the agent’s behaviour, by building an agent with a policy based on the PG and comparing the behaviour of the two agents.