Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning
Tyler Kastner, Murat A Erdogdu, Amir-massoud Farahmand
Abstract
We consider the problem of learning models for risk-sensitive reinforcement learning. We theoretically demonstrate that proper value equivalence, a method of learning models which can be used to plan optimally in the risk-neutral setting, is not sufficient to plan optimally in the risk-sensitive setting. We leverage distributional reinforcement learning to introduce two new notions of model equivalence, one which is general and can be used to plan for any risk measure, but is intractable; and a practical variation which allows one to choose which risk measures they may plan optimally for. We demonstrate how our models can be used to augment any model-free risk-sensitive algorithm, and provide both tabular and large-scale experiments to demonstrate our method’s ability.
BibTeX
@inproceedings{
kastner2023distributional,
title={Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning},
author={Tyler Kastner and Murat A Erdogdu and Amir-massoud Farahmand},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=SLTQluG80x}
}