Abstract

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.
Original languageEnglish
Publication statusAccepted/In press - 4 Sep 2020
Event1st TAILOR Workshop at ECAI 2020 - Santiago de Compostela, Spain
Duration: 4 Sep 20205 Sep 2020
https://liu.se/en/research/tailor/workshop

Workshop

Workshop1st TAILOR Workshop at ECAI 2020
Abbreviated titleTAILOR 2020
CountrySpain
CitySantiago de Compostela
Period4/09/205/09/20
Internet address

Fingerprint Dive into the research topics of 'Modelling Agent Policies with Interpretable Imitation Learning'. Together they form a unique fingerprint.

Cite this