# Inverse Reinforcement Learning with Explicit Policy Estimates

arXiv: https://arxiv.org/abs/2103.02863 · HTML: https://mlsanity.com/paper/2103.02863/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 6 of its 28 references that are in the map.
- First posted on arXiv 4 Mar 2021.

## Placed in

- Offline RL and imitation learning from data / [Inverse reinforcement learning](https://mlsanity.com/offlinerl/inverse-reinforcement-learning/)

## Builds on (most cited first, 6 of 6)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Reinforcement Learning with Deep Energy-Based Policies](https://mlsanity.com/paper/1702.08165/) (2017)
- [Maximum Entropy Deep Inverse Reinforcement Learning](https://mlsanity.com/paper/1507.04888/) (2015)
- [Quantifying Differences in Reward Functions](https://mlsanity.com/paper/2006.13900/) (2020)
- [Inverse Reinforcement Learning with Conditional Choice Probabilities](https://mlsanity.com/paper/1709.07597/) (2017)

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

- [Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees](https://mlsanity.com/paper/2210.01808/) (2022)
- [Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees](https://mlsanity.com/paper/2210.01282/) (2022)
- [Analyzing sequential activity and travel decisions with interpretable deep inverse reinforcement learning](https://mlsanity.com/paper/2503.12761/) (2025)

## Abstract (arXiv)

Various methods for solving the inverse reinforcement learning (IRL) problem have been developed independently in machine learning and economics. In particular, the method of Maximum Causal Entropy IRL is based on the perspective of entropy maximization, while related advances in the field of economics instead assume the existence of unobserved action shocks to explain expert behavior (Nested Fixed Point Algorithm, Conditional Choice Probability method, Nested Pseudo-Likelihood Algorithm). In this work, we make previously unknown connections between these related methods from both fields. We achieve this by showing that they all belong to a class of optimization problems, characterized by a common form of the objective, the associated policy and the objective gradient. We demonstrate key computational and algorithmic differences which arise between the methods due to an approximation of the optimal soft value function, and describe how this leads to more efficient algorithms. Using insights which emerge from our study of this class of optimization problems, we identify various problem scenarios and investigate each method's suitability for these problems.