Q-learning with nearest neighbors
Author(s)
Shah, Devavrat; Xie, Qiaomin![Thumbnail](/bitstream/handle/1721.1/137946/7574-q-learning-with-nearest-neighbors.pdf.jpg?sequence=4&isAllowed=y)
DownloadPublished version (514.1Kb)
Publisher Policy
Publisher Policy
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Terms of use
Metadata
Show full item recordAbstract
© 2018 Curran Associates Inc.All rights reserved. We consider model-free reinforcement learning for infinite-horizon discounted Markov Decision Processes (MDPs) with a continuous state space and unknown transition kernel, when only a single sample path under an arbitrary policy of the system is available. We consider the Nearest Neighbor Q-Learning (NNQL) algorithm to learn the optimal Q function using nearest neighbor regression method. As the main contribution, we provide tight finite sample analysis of the convergence rate. In particular, for MDPs with a d-dimensional state space and the discounted factor γ ∈ (0, 1), given an arbitrary sample path with “covering time” L, we establish that the algorithm is guaranteed to output an ε-accurate estimate of the optimal Q-function using Õ e (L/(ε 3 (1 - γ) 7 )) samples. For instance, for a well-behaved MDP, the covering time of the sample path under the purely random policy scales as Õ e (1/ε d ), so the sample complexity scales as Õ e (1/ε d+3 ). Indeed, we establish a lower bound that argues that the dependence of Ω e (1/ε d+2 ) is necessary.
Date issued
2018Department
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science; Statistics and Data Science Center (Massachusetts Institute of Technology)Citation
Shah, Devavrat and Xie, Qiaomin. 2018. "Q-learning with nearest neighbors."
Version: Final published version