Lawrence K. Saul, Satinder P. Singh  Home/Search
Context Related
| colorado.edu/users/bavej...COLT96.ps.gz colorado.edu/~baveja/./P...COLT96.ps.gz 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: colorado.edu/~baveja/papers (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: Markov decision processes (MDPs) with undiscounted rewards represent an important class of problems in decision and control. The goal of learning in these MDPs is to find a policy that yields the maximum expected return per unit time. In large state spaces, computing these averages directly is not feasible; instead, the agent must estimate them by stochastic exploration of the state space. In this case, longer exploration times enable more accurate estimates and more informed decision-making.... (Update)
Context of citations to this paper: More
.... classes of MDP s, if the model of learning is modified from the standard one, or if one changes the criteria for success (Saul Singh, 1996; Fiechter, 1994; Fiechter, 1997; Schapire Warmuth, 1994; Singh Dayan, in press) Fiechter (1994,1997) whose results are...
...j ) i G ij 1 [ Q j ] I Q j, i ] 1 ] ii (D j, i ) j G ji 1 [ Q i ] I Q i, j ] 1 ] jj . Notes 1. See Saul Singh (1996) for learning curve bounds for an interesting Markov decision process that are derived using techniques from statistical mechanics. 2. There are other...
Cited by: More
Near-Optimal Reinforcement Learning in Polynomial Time - Kearns, Singh (1998) (Correct)
Analytical Mean Squared Error Curves for Temporal Difference.. - Singh, Dayan (1988) (Correct)
Similar documents (at the sentence level):
6.8%: Markov Decision Processes in Large State Spaces - Saul, Singh (1995) (Correct)
Active bibliography (related documents): More All
0.0: Learning to Take Actions - Khardon (1998) (Correct)
0.0: Reinforcement Learning: A Survey - Leslie Pack Kaelbling, Michael L.. (1996) (Correct)
0.0: Planning and Scheduling - Dean, Kambhampati (1996) (Correct)
Similar documents based on text: More All
0.4: Polynomial-Time Reinforcement Learning of Near-Optimal Policies - Pivazyan, Shoham (Correct)
0.2: Reinforcement Learning and Mistake Bounded Algorithms - Mansour (1999) (Correct)
0.2: A Near-Optimal Polynomial Time Algorithm for Learning in.. - Brafman, Tennenholtz (1999) (Correct)
Related documents from co-citation: More All
3: the convergence of stochastic iterative dynamic programming algorithms - Jaakkola, Jordan et al. - 1994
3: Asynchronous stochastic approximation and Q-learning (context) - Tsitsiklis - 1994
2: Machine Learning (context) - Watkins, Dayan - 1992
BibTeX entry: (Update)
Saul, L., Singh, S. (1996). Learning curve bounds for Markov decision processes with undiscounted rewards. In COLT96. http://citeseer.ist.psu.edu/saul96learning.html More
@inproceedings{ saul96learning,
author = "Lawrence K. Saul and Satinder P. Singh",
title = "Learning Curve Bounds for a Markov Decision Process with Undiscounted Rewards",
booktitle = "Computational Learing Theory",
pages = "147-156",
year = "1996",
url = "citeseer.ist.psu.edu/saul96learning.html" }
Citations (may not include all citations):563 Learning to predict by the methods of temporal differences - Sutton - 1988
278 Dynamic programming and optimal control (context) - Bertsekas - 1995
257 Learning to act using real-time dynamic programming - Barto, Bradtke et al. - 1995
120 Large deviation techniques in decision (context) - Bucklew - 1990
70 Statistical Mechanics (context) - Huang - 1987
60 A survey of matrix theory and matrix inequalities (context) - Marcus, Minc - 1992
58 Statistical mechanics of learning from examples (context) - Seung, Sompolinsky et al. - 1992
47 Rigorous learning curve bounds from statistical mechanics - Haussler, Kearns et al. - 1994
40 The statistical mechanics of learning a rule (context) - Watkin, Rau et al. - 1993
23 Reinforcement learning algorithms for average-payoff markovi.. - Singh - 1994
11 Efficient reinforcement learning - Fiechter - 1994
1 A Eigenvalues In this appendix we derive eq (context) - Watkins, Dayan et al. - 1992
1 Markov decision processes in large state spaces - Saul, Singh - 1995
Documents on the same site (http://www.cs.colorado.edu/~baveja/papers.html): More
An Upper Bound on the Loss from Approximate Optimal-Value.. - Singh, Yee (1994) (Correct)
Theoretical Results on Reinforcement Learning with.. - Precup, Sutton, Singh (1998) (Correct)
Soft Dynamic Programming Algorithms: Convergence Proofs - Singh (1993) (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