# Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning

arXiv: https://arxiv.org/abs/2310.19831 · HTML: https://mlsanity.com/paper/2310.19831/

## 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 (most cited first, 18 of 18)

- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning](https://mlsanity.com/paper/1809.02925/) (2018)
- [A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models](https://mlsanity.com/paper/1611.03852/) (2016)
- [What do we need to build explainable AI systems for the medical domain?](https://mlsanity.com/paper/1712.09923/) (2017)
- [Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction](https://mlsanity.com/paper/1703.01030/) (2017)
- [Strictly Batch Imitation Learning by Energy-based Distribution Matching](https://mlsanity.com/paper/2006.14154/) (2020)
- [Learning the Preferences of Ignorant, Inconsistent Agents](https://mlsanity.com/paper/1512.05832/) (2015)
- [Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information](https://mlsanity.com/paper/1810.01266/) (2018)
- [Sample-Efficient Imitation Learning via Generative Adversarial Nets](https://mlsanity.com/paper/1809.02064/) (2018)
- [Adversarial Imitation via Variational Inverse Reinforcement Learning](https://mlsanity.com/paper/1809.06404/) (2018)
- [SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards](https://mlsanity.com/paper/1905.11108/) (2019)
- [Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and Dynamics](https://mlsanity.com/paper/1604.03912/) (2016)
- [Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics](https://mlsanity.com/paper/1908.04696/) (2019)
- [Inverse Active Sensing: Modeling and Understanding Timely Decision-Making](https://mlsanity.com/paper/2006.14141/) (2020)
- [Assisted Perception: Optimizing Observations to Communicate State](https://mlsanity.com/paper/2008.02840/) (2020)
- [Probabilistic inverse reinforcement learning in unknown environments](https://mlsanity.com/paper/1307.3785/) (2013)

## Built on by (most cited first, 3 of 3)

- [Defining Expertise: Applications to Treatment Effect Estimation](https://mlsanity.com/paper/2403.00694/) (2024)
- [BET: Explaining Deep Reinforcement Learning through The Error-Prone Decisions](https://mlsanity.com/paper/2401.07263/) (2024)
- [Quantifying Potential Observation Missingness in Inverse Reinforcement Learning](https://mlsanity.com/paper/2605.12831/) (2026)

## 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.