Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learning

by   Zaiyan Xu, et al.

We consider the problem of learning a control policy that is robust against the parameter mismatches between the training environment and testing environment. We formulate this as a distributionally robust reinforcement learning (DR-RL) problem where the objective is to learn the policy which maximizes the value function against the worst possible stochastic model of the environment in an uncertainty set. We focus on the tabular episodic learning setting where the algorithm has access to a generative model of the nominal (training) environment around which the uncertainty set is defined. We propose the Robust Phased Value Learning (RPVL) algorithm to solve this problem for the uncertainty sets specified by four different divergences: total variation, chi-square, Kullback-Leibler, and Wasserstein. We show that our algorithm achieves 𝒊Ėƒ(|ð’Ū||𝒜| H^5) sample complexity, which is uniformly better than the existing results by a factor of |ð’Ū|, where |ð’Ū| is number of states, |𝒜| is the number of actions, and H is the horizon length. We also provide the first-ever sample complexity result for the Wasserstein uncertainty set. Finally, we demonstrate the performance of our algorithm using simulation experiments.


page 1

page 2

page 3

page 4

∙ 12/02/2021

Sample Complexity of Robust Reinforcement Learning with a Generative Model

The Robust Markov Decision Process (RMDP) framework focuses on designing...
∙ 02/26/2023

A Finite Sample Complexity Bound for Distributionally Robust Q-learning

We consider a reinforcement learning setting in which the deployment env...
∙ 02/10/2023

Towards Minimax Optimality of Model-based Robust Reinforcement Learning

We study the sample complexity of obtaining an Ïĩ-optimal policy in Robus...
∙ 05/26/2023

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

This paper investigates model robustness in reinforcement learning (RL) ...
∙ 09/15/2023

Wasserstein Distributionally Robust Policy Evaluation and Learning for Contextual Bandits

Off-policy evaluation and learning are concerned with assessing a given ...
∙ 03/15/2023

On the Benefits of Leveraging Structural Information in Planning Over the Learned Model

Model-based Reinforcement Learning (RL) integrates learning and planning...
∙ 05/12/2018

Do Outliers Ruin Collaboration?

We consider the problem of learning a binary classifier from n different...

Please sign up or login with your details

Forgot password? Click here to reset