John N. Tsitsiklis, Benjamin Van Roy  Home/Search
Context Related
| mit.edu/people/jnt...97bvrtdpre.pdf Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: mit.edu/people/jnt/publ (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: Wediscuss thetemporal-difference learning algorithm, as applied toapproximatingthe cost-to-go function of an infinite-horizon discounted Markovchain. The algorithm weanalyze updates parametersofalinear function approximator on--line, duringasingle endless trajectory of an irreducible aperiodic Markovchain withafiniteorinfinitestate space. Wepresent a proof of convergence (with probability1),acharacterization of the limit of convergence, andaboundontheresultingapproximation error. Furthermore,... (Update)
Cited by: More
Least-Squares Temporal Difference Learning - Justin Boyan Nasa (Correct)
Planning In Hybrid Structured Stochastic - Domains Comenius University (Correct)
A Convergent Form of Approximate Policy - Iteration Theodore Perkins (Correct)
Similar documents (at the sentence level):
48.7%: An Analysis of Temporal-Difference Learning with Function.. - Tsitsiklis, Van Roy (1996) (Correct)
7.0%: Learning and Value Function Approximation in Complex Decision.. - Van Roy (1998) (Correct)
Similar documents based on text: More All
0.5: Lids-P-2390 - May Average Cost (Correct)
0.4: March2,1999 - On Average Versus (Correct)
0.4: On Step-Size and Bias in Temporal-Difference Learning - Richard Sutton (1994) (Correct)
Related documents from co-citation: More All
33: Learning to predict by the method of temporal differences - Sutton - 1988
29: Neuro-Dynamic Programming (context) - Bertsekas, Tsitsiklis - 1996
18: Reinforcement learning: An introduction - Sutton, Barto - 1998
BibTeX entry: (Update)
J. N. Tsitsiklis and B. Van Roy. An analysis of temporal-difference learning with function approximation. Technical Report LIDS-P-2322, MIT, 1996. http://citeseer.ist.psu.edu/tsitsiklis96analysis.html More
@techreport{ tsitsiklis96analysis,
author = "John N. Tsitsiklis and Benjamin Van Roy",
title = "An analysis of temporal-difference learning with function approximation",
number = "LIDS-P-2322",
year = "1996",
url = "citeseer.ist.psu.edu/tsitsiklis96analysis.html" }
Citations not processed or no citations identified.
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://anxiety-closet.mit.edu/people/jnt/publ.html): More
Boundedness of Finitely Generated Matrix Semigroups is.. - Blondel, Tsitsiklis (1999) (Correct)
A Neuro-Dynamic Programming Approach to Call Admission.. - Marbach, Tsitsiklis (1997) (Correct)
Deciding Stability and Mortality of Piecewise.. - Blondel, Bournez, .. (1998) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC