Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Zhengfei, Panaganti, Kishan, Shi, Laixi, Sui, Yanan, Wierman, Adam, Yue, Yisong
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2406.15788
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917701702647808
author Zhang, Zhengfei
Panaganti, Kishan
Shi, Laixi
Sui, Yanan
Wierman, Adam
Yue, Yisong
author_facet Zhang, Zhengfei
Panaganti, Kishan
Shi, Laixi
Sui, Yanan
Wierman, Adam
Yue, Yisong
contents We study the problem of Distributionally Robust Constrained RL (DRC-RL), where the goal is to maximize the expected reward subject to environmental distribution shifts and constraints. This setting captures situations where training and testing environments differ, and policies must satisfy constraints motivated by safety or limited budgets. Despite significant progress toward algorithm design for the separate problems of distributionally robust RL and constrained RL, there do not yet exist algorithms with end-to-end convergence guarantees for DRC-RL. We develop an algorithmic framework based on strong duality that enables the first efficient and provable solution in a class of environmental uncertainties. Further, our framework exposes an inherent structure of DRC-RL that arises from the combination of distributional robustness and constraints, which prevents a popular class of iterative methods from tractably solving DRC-RL, despite such frameworks being applicable for each of distributionally robust RL and constrained RL individually. Finally, we conduct experiments on a car racing benchmark to evaluate the effectiveness of the proposed algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2406_15788
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Distributionally Robust Constrained Reinforcement Learning under Strong Duality
Zhang, Zhengfei
Panaganti, Kishan
Shi, Laixi
Sui, Yanan
Wierman, Adam
Yue, Yisong
Machine Learning
We study the problem of Distributionally Robust Constrained RL (DRC-RL), where the goal is to maximize the expected reward subject to environmental distribution shifts and constraints. This setting captures situations where training and testing environments differ, and policies must satisfy constraints motivated by safety or limited budgets. Despite significant progress toward algorithm design for the separate problems of distributionally robust RL and constrained RL, there do not yet exist algorithms with end-to-end convergence guarantees for DRC-RL. We develop an algorithmic framework based on strong duality that enables the first efficient and provable solution in a class of environmental uncertainties. Further, our framework exposes an inherent structure of DRC-RL that arises from the combination of distributional robustness and constraints, which prevents a popular class of iterative methods from tractably solving DRC-RL, despite such frameworks being applicable for each of distributionally robust RL and constrained RL individually. Finally, we conduct experiments on a car racing benchmark to evaluate the effectiveness of the proposed algorithm.
title Distributionally Robust Constrained Reinforcement Learning under Strong Duality
topic Machine Learning
url https://arxiv.org/abs/2406.15788