Michael Kearns, Satinder Singh  Home/Search
Context Related
| colorado.edu/users/ba...ICML98_KS.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: sneaker.mindmaker.kfkip...Summary (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: We present new algorithms for reinforcement learning, and prove that they have polynomial bounds on the resources required to achieve near-optimal return in general Markov decision processes. After observing that the number of actions required to approach the optimal return is lower bounded by the mixing time T of the optimal policy (in the undiscounted case) or by the horizon time T (in the discounted case), we then give algorithms requiring a number of actions and total computation time that... (Update)
Cited by: More
Journal of Machine Learning Research 7 (2006) 1079--1105.. - Multi-Armed Bandit And (Correct)
BL-WoLF: A Framework For Loss-Bounded Learnability In.. - Vincent Conitzer Conitzer (2003) (Correct)
P3VI: A Partitioned, Prioritized, Parallel Value Iterator - Wingate, Seppi (2004) (Correct)
Similar documents (at the sentence level):
56.0%: Near-Optimal Reinforcement Learning in Polynomial Time - Kearns, Singh (1998) (Correct)
Active bibliography (related documents): More All
0.5: Reinforcement Learning: A Survey - Kaelbling, Littman, Moore (1996) (Correct)
0.3: Analytical Mean Squared Error Curves for Temporal Difference.. - Singh, Dayan (1988) (Correct)
0.1: Open Theoretical Questions in Reinforcement Learning - Sutton (1999) (Correct)
Similar documents based on text: More All
0.4: Polynomial-Time Reinforcement Learning of Near-Optimal Policies - Pivazyan, Shoham (Correct)
0.3: Faster Near-Optimal Reinforcement Learning: Adding Adaptiveness.. - Domingo (Correct)
0.2: Exact Inference of Hidden Structure - From Sample Data (Correct)
Related documents from co-citation: More All
11: Markov games as a framework for multi-agent reinforcement learning - Littman - 1994
10: Reinforcement learning: a survey - Kaelbling, Littman et al. - 1996
10: Multiagent reinforcement learning: Theoretical framework and an algorithm - Hu, Wellman - 1998
BibTeX entry: (Update)
Kearns, M., and Singh, S. 1998. Near-optimal reinforcement learning in polynomial time. In ICML-98, 260--268. http://citeseer.ist.psu.edu/article/kearns98nearoptimal.html More
@inproceedings{ kearns98nearoptimal,
author = "Michael Kearns and Satinder Singh",
title = "Near-optimal reinforcement learning in polynomial time",
booktitle = "Proc. 15th International Conf. on Machine Learning",
publisher = "Morgan Kaufmann, San Francisco, CA",
pages = "260--268",
year = "1998",
url = "citeseer.ist.psu.edu/article/kearns98nearoptimal.html" }
Citations (may not include all citations):614 Reinforcement Learning: An Introduction - Sutton, Barto - 1998
413 Neuro-Dynamic Programming (context) - Bertsekas, Tsitsiklis - 1996
281 Machine Learning (context) - Watkins, Dayan - 1992
107 the convergence of stochastic iterative dynamic programming .. - Jaakkola, Jordan et al. - 1994
80 The role of exploration in learning control - Thrun - 1992
71 Asynchronous stochastic approximation and Q-learning (context) - Tsitsiklis - 1994
23 Sequential decision problems and neural networks (context) - Barto, Sutton et al. - 1990
13 Convergence of indirect adaptive asynchronous value iteratio.. (context) - Gullapalli, Barto - 1994
7 Analytical mean squared error curves for temporal di#erence .. - Singh, Dayan - 1988
3 Learning curve bounds for Markov decision processes with und.. - Saul, Singh - 1996
2 Prioritized sweeping: Reinforcement learning with less data .. (context) - Computation, Moore et al. - 1993
2 Markov decision processes : discrete stochastic dynamic prog.. (context) - Learning - 1994
2 cient reinforcement learning (context) - Fiechter - 1994
2 Expected mistake bound model for online reinforcement learni.. (context) - Fiechter - 1997
1 the worstcase analysis of temporal-di#erence learning algori.. (context) - Schapire, Warmuth - 1994
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://sneaker.mindmaker.kfkipark.hu/~szepes/research/Summary.htm): More
Finding Structure in Reinforcement Learning - Thrun, Schwartz (1995) (Correct)
Finite-time Regret Bounds for the Multiarmed Bandit Problem - Cesa-Bianchi, Fischer (1998) (Correct)
Module Based Reinforcement Learning for a Real Robot - Kalm'ar (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