Convergence Results for Some Temporal Difference Methods Based on Least Squares
Author(s)
Yu, Huizhen; Bertsekas, Dimitri P.
DownloadYu-2009-Convergence Results for Some Temporal Difference Methods Based on Least Squares.pdf (1.316Mb)
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
We consider finite-state Markov decision processes, and prove convergence and rate of convergence results for certain least squares policy evaluation algorithms of the type known as LSPE(lambda ). These are temporal difference methods for constructing a linear function approximation of the cost function of a stationary policy, within the context of infinite-horizon discounted and average cost dynamic programming. We introduce an average cost method, patterned after the known discounted cost method, and we prove its convergence for a range of constant stepsize choices. We also show that the convergence rate of both the discounted and the average cost methods is optimal within the class of temporal difference methods. Analysis and experiment indicate that our methods are substantially and often dramatically faster than TD(lambda), as well as more reliable.
Date issued
2009-07Department
Massachusetts Institute of Technology. Laboratory for Information and Decision SystemsJournal
IEEE Transactions on Automatic Control
Publisher
Institute of Electrical and Electronics Engineers
Citation
Huizhen Yu, and D.P. Bertsekas. “Convergence Results for Some Temporal Difference Methods Based on Least Squares.” IEEE Transactions on Automatic Control 54.7 (2009): 1515–1531. Web.©2009 IEEE.
Version: Final published version
Other identifiers
INSPEC Accession Number: 10774680
ISSN
0018-9286