Concept Learning for Interpretable Multi-Agent Reinforcement Learning
This addresses the need for interpretable AI in multi-agent systems operating near humans, though it is incremental as it builds on existing reinforcement learning methods.
The paper tackles the problem of inscrutable deep neural network policies in multi-agent robotic systems by introducing a method that incorporates interpretable concepts from domain experts into multi-agent reinforcement learning, resulting in improved interpretability, training stability, policy performance, and sample efficiency in simulated and real-world cooperative-competitive games.
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.