# Risk-sensitive Inverse Reinforcement Learning via Semi- and Non-Parametric Methods

arXiv: https://arxiv.org/abs/1711.10055 · HTML: https://mlsanity.com/paper/1711.10055/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2017.

## Built on by (most cited first, 12 of 12)

- [Efficient Risk-Averse Reinforcement Learning](https://mlsanity.com/paper/2205.05138/) (2022)
- [Human irrationality: both bad and good for reward inference](https://mlsanity.com/paper/2111.06956/) (2021)
- [On the Sensitivity of Reward Inference to Misspecified Human Models](https://mlsanity.com/paper/2212.04717/) (2022)
- [Risk-Sensitive Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1808.04468/) (2018)
- [Inverse Decision Modeling: Learning Interpretable Representations of Behavior](https://mlsanity.com/paper/2310.18591/) (2023)
- [Eliciting Risk Aversion with Inverse Reinforcement Learning via Interactive Questioning](https://mlsanity.com/paper/2308.08427/) (2023)
- [Inverse Concave-Utility Reinforcement Learning is Inverse Game Theory](https://mlsanity.com/paper/2405.19024/) (2024)
- [Active Learning for Risk-Sensitive Inverse Reinforcement Learning](https://mlsanity.com/paper/1909.07843/) (2019)
- [Supervised Reward Inference](https://mlsanity.com/paper/2502.18447/) (2025)
- [Distributional Inverse Reinforcement Learning](https://mlsanity.com/paper/2510.03013/) (2025)
- [Active Constraint Learning in High Dimensions from Demonstrations](https://mlsanity.com/paper/2512.22757/) (2025)
- [Strategically Robust Multi-Agent Reinforcement Learning with Linear Function Approximation](https://mlsanity.com/paper/2603.09208/) (2026)

## Abstract (arXiv)

The literature on Inverse Reinforcement Learning (IRL) typically assumes that humans take actions in order to minimize the expected value of a cost function, i.e., that humans are risk neutral. Yet, in practice, humans are often far from being risk neutral. To fill this gap, the objective of this paper is to devise a framework for risk-sensitive IRL in order to explicitly account for a human's risk sensitivity. To this end, we propose a flexible class of models based on coherent risk measures, which allow us to capture an entire spectrum of risk preferences from risk-neutral to worst-case. We propose efficient non-parametric algorithms based on linear programming and semi-parametric algorithms based on maximum likelihood for inferring a human's underlying risk measure and cost function for a rich class of static and dynamic decision-making settings. The resulting approach is demonstrated on a simulated driving game with ten human participants. Our method is able to infer and mimic a wide range of qualitatively different driving styles from highly risk-averse to risk-neutral in a data-efficient manner. Moreover, comparisons of the Risk-Sensitive (RS) IRL approach with a risk-neutral model show that the RS-IRL framework more accurately captures observed participant behavior both qualitatively and quantitatively, especially in scenarios where catastrophic outcomes such as collisions can occur.