Concept Learning for Interpretable Multi-Agent Reinforcement Learning

Renos Zabounidis, Joseph Campbell, Simon Stepputtis, Dana Hughes, Katia P. Sycara

Keywords: Multi-Agent Reinforcement Learning, Interpretable Machine Learning

TL;DR: We introduce a method for incorporating interpretable concepts from a domain expert into models trained through multi-agent reinforcement learning by requiring the model to first predict such concepts then utilize them for decision making.

Abstract: Multi-agent robotic systems are increasingly operating in real-world environments in close proximity to humans, yet are largely controlled by policy models with inscrutable deep neural network representations. We introduce a method for incorporating interpretable concepts from a domain expert into models trained through multi-agent reinforcement learning, by requiring the model to first predict such concepts then utilize them for decision making. This allows an expert to both reason about the resulting concept policy models in terms of these high-level concepts at run-time, as well as intervene and correct mispredictions to improve performance. We show that this yields improved interpretability and training stability, with benefits to policy performance and sample efficiency in a simulated and real-world cooperative-competitive multi-agent game.

Student First Author: yes