mlsanityData to 14 Oct 2026

Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning

arXiv 2310.19831 ↗First posted 28 Oct 2023stat.ML cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Understanding human behavior from observed data is critical for transparency and accountability in decision-making. Consider real-world settings such as healthcare, in which modeling a decision-maker's policy is challenging -- with no access to underlying states, no knowledge of environment dynamics, and no allowance for live experimentation. We desire learning a data-driven representation of decision-making behavior that (1) inheres transparency by design, (2) accommodates partial observability, and (3) operates completely offline. To satisfy these key criteria, we propose a novel model-based Bayesian method for interpretable policy learning ("Interpole") that jointly estimates an agent's (possibly biased) belief-update process together with their (possibly suboptimal) belief-action mapping. Through experiments on both simulated and real-world data for the problem of Alzheimer's disease diagnosis, we illustrate the potential of our approach as an investigative device for auditing, quantifying, and understanding human decision-making behavior.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 18 of its 61 references that are in the map. First posted on arXiv 28 Oct 2023.

Builds on

18 of 61 references.

References · 18

  1. 2016Generative Adversarial Imitation Learningcited by 1,597
  2. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 490
  3. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 345
  4. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learningcited by 204
  5. 2016A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Modelscited by 168
  6. 2017What do we need to build explainable AI systems for the medical domain?cited by 129
  7. 2017Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Predictioncited by 93
  8. 2020Strictly Batch Imitation Learning by Energy-based Distribution Matchingcited by 54
  9. 2015Learning the Preferences of Ignorant, Inconsistent Agentscited by 45
  10. 2018Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Informationcited by 41
  11. 2018Sample-Efficient Imitation Learning via Generative Adversarial Netscited by 36
  12. 2018Adversarial Imitation via Variational Inverse Reinforcement Learningcited by 36
6 more
  1. 2019SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewardscited by 28
  2. 2016Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and Dynamicscited by 24
  3. 2019Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamicscited by 16
  4. 2020Inverse Active Sensing: Modeling and Understanding Timely Decision-Makingcited by 12
  5. 2020Assisted Perception: Optimizing Observations to Communicate Statecited by 10
  6. 2013Probabilistic inverse reinforcement learning in unknown environmentscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 1.

3 papers.

  1. 2024Defining Expertise: Applications to Treatment Effect Estimationcited by 2
  2. 2024BET: Explaining Deep Reinforcement Learning through The Error-Prone Decisionscited by 0
  3. 2026Quantifying Potential Observation Missingness in Inverse Reinforcement Learningcited by 0