Modelling Agent Policies with Interpretable Imitation Learning

Published in EasyChair Preprint no. 2959, 2020

Recommended citation: Bewley, Tom and Lawry, Jonathan and Richards, Arthur. "Modelling Agent Policies with Interpretable Imitation Learning." EasyChair Preprint no. 2959. 2020. [PDF]

As we deploy autonomous agents in safety-critical domains, it becomes important to develop an understanding of their internal mechanisms and representations. We outline an approach to imitation learning for reverse-engineering black box agent policies in MDP environments, yielding simplified, interpretable models in the form of decision trees. As part of this process, we explicitly model and learn agents’ latent state representations by selecting from a large space of candidate features constructed from the Markov state. We present initial promising results from an implementation in a multi-agent traffic environment.