Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published March 2020 | Submitted
Journal Article Open

Inverse Risk-Sensitive Reinforcement Learning


This work addresses the problem of inverse reinforcement learning in Markov decision processes where the decision-making agent is risk-sensitive. In particular, a risk-sensitive reinforcement learning algorithm with convergence guarantees that makes use of coherent risk metrics and models of human decision-making which have their origins in behavioral psychology and economics is presented. The risk-sensitive reinforcement learning algorithm provides the theoretical underpinning for a gradient-based inverse reinforcement learning algorithm that seeks to minimize a loss function defined on the observed behavior. It is shown that the gradient of the loss function with respect to the model parameters is well defined and computable via a contraction map argument. Evaluation of the proposed technique is performed on a Grid World example, a canonical benchmark problem.

Additional Information

© 2019 IEEE. Manuscript received July 31, 2018; revised August 1, 2018, August 2, 2018, June 6, 2019, and June 9, 2019; accepted June 22, 2019. Date of publication July 3, 2019; date of current version February 27, 2020. This work was supported by National Science Foundation Award CNS-1656873. Recommended by Associate Editor Prof. Samer S. Saab.

Attached Files

Submitted - 1703.09842.pdf


Files (1.6 MB)
Name Size Download all
1.6 MB Preview Download

Additional details

August 19, 2023
October 20, 2023