2021-07-01-badrinath21a.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees	This paper addresses the problem of model-free reinforcement learning for Robust Markov Decision Process (RMDP) with large state spaces. The goal of the RMDPs framework is to find a policy that is robust against the parameter uncertainties due to the mismatch between the simulator model and real-world settings. We first propose the Robust Least Squares Policy Evaluation algorithm, which is a multi-step online model-free learning algorithm for policy evaluation. We prove the convergence of this algorithm using stochastic approximation techniques. We then propose Robust Least Squares Policy Iteration (RLSPI) algorithm for learning the optimal robust policy. We also give a general weighted Euclidean norm bound on the error (closeness to optimality) of the resulting policy. Finally, we demonstrate the performance of our RLSPI algorithm on some benchmark problems from OpenAI Gym.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	badrinath21a	0	Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees	511	520	511-520	511	false	Badrinath, Kishan Panaganti and Kalathil, Dileep	given family Kishan Panaganti Badrinath given family Dileep Kalathil	2021-07-01		Proceedings of the 38th International Conference on Machine Learning	139	inproceedings	date-parts 2021 7 1	http://proceedings.mlr.press/v139/badrinath21a/badrinath21a.pdf	label link Supplementary PDF http://proceedings.mlr.press/v139/badrinath21a/badrinath21a-supp.pdf