Utilising Assured Multi-Agent Reinforcement Learning within safety-critical scenarios

Abstract

Multi-agent reinforcement learning allows a team of agents to learn how to work together to solve complex decision-making problems in a shared environment. However, this learning process utilises stochastic mechanisms, meaning that its use in safety-critical domains can be problematic. To overcome this issue, we propose an Assured Multi-Agent Reinforcement Learning (AMARL) approach that uses a model checking technique called quantitative verification to provide formal guarantees of agent compliance with safety, performance, and other non-functional requirements during and after the reinforcement learning process. We demonstrate the applicability of our AMARL approach in three different patrolling navigation domains in which multi-agent systems must learn to visit key areas by using different types of reinforcement learning algorithms (temporal difference learning, game theory, and direct policy search). Furthermore, we compare the effectiveness of these algorithms when used in combination with and without our approach. Our extensive experiments with both homogeneous and heterogeneous multi-agent systems of different sizes show that the use of AMARL leads to safety requirements being consistently satisfied and to better overall results than standard reinforcement learning.