mlsanityData to 7 Oct 2026

Modelling Agent Policies with Interpretable Imitation Learning

arXiv 2006.11309 ↗First posted 19 Jun 2020cs.AIcited by 6

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 2 of its 8 references that are in the map. First posted on arXiv 19 Jun 2020.

Builds on

2 of 8 references.

References · 2

  1. 2017Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Modelscited by 202
  2. 2018State Representation Learning for Control: An Overviewcited by 125

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 0; 2023: 3; 2024: 1.

6 papers.

  1. 2021Inverse Contextual Bandits: Learning How Behavior Evolves over Timecited by 12
  2. 2021The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulationcited by 11
  3. 2023Inverse Decision Modeling: Learning Interpretable Representations of Behaviorcited by 10
  4. 2023Explaining Imitation Learning through Framescited by 1
  5. 2023Symbolic Imitation Learning: From Black-Box to Explainable Driving Policiescited by 1
  6. 2024Interpretable Robotic Manipulation from Languagecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2018Learning Policy Representations in Multiagent Systems
  2. 2018Imitating Latent Policies from Observation
  3. 2020Robust Asymmetric Learning in POMDPs
  4. 2026InterPReT: Interactive Policy Restructuring and Training Enable Effective Imitation Learning from Laypersons
  5. 2024A Dual Approach to Imitation Learning from Observations with Offline Datasets
  6. 2019Imitation Learning of Factored Multi-agent Reactive Models
  7. 2025Making Universal Policies Universal
  8. 2024Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model