Dynamic Programming Algorithms Tommi Jaakkola Michael I. Jordan Department of ...  Home/Search
Context
Related
| berkeley.edu/~jord...mputation94.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: berkeley.edu/~jord...publications (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms, including the TD() algorithm of Sutton (1988) and the Q-learning algorithm of Watkins (1989), can be motivated heuristically as approximations to dynamic programming (DP). In this paper we provide a rigorous proof of convergence of these DP-based learning algorithms by relating them to the powerful techniques of... (Update)
Similar documents (at the sentence level):
55.6%: On the Convergence of Stochastic Iterative Dynamic.. - Jaakkola, Jordan (1994) (Correct)
12.2%: Convergence of Stochastic Iterative Dynamic Programming.. - Jaakkola, Jordan, Singh (1994) (Correct)
Active bibliography (related documents): More All
0.1: A New Parameter Estimation Method for Gaussian Mixtures - Singer, Warmuth (1998) (Correct)
0.1: Update rules for parameter estimation in Bayesian networks - Bauer, Koller, Singer (1997) (Correct)
0.1: Learning To Solve Markovian Decision Processes - Singh (1994) (Correct)
System load high. Please wait...
Timeout. Please try your query later.
Similar documents based on text:
0.0: Unknown - (Correct)
BibTeX entry: (Update)
@misc{ algorithms-convergence,
author = "Dynamic Programming Algorithms",
title = "On the Convergence of Stochastic Iterative",
url = "citeseer.ist.psu.edu/757046.html" }
Citations (may not include all citations):658 Learning from delayed rewards (context) - Watkins - 1989
563 Learning to predict by the methods of temporal differences - Sutton - 1988
348 Parallel and Distributed Computation: Numerical Methods (context) - Bertsekas, Tsitsiklis - 1989
281 Machine Learning (context) - Watkins, Dayan - 1992
257 Learning to act using real-time dynamic programming - Barto, Bradtke et al. - 1993
230 Dynamic Programming: Deterministic and Stochastic Models (context) - Bertsekas - 1987
101 Applied Probability Models with Optimization Applications (context) - Ross - 1970
71 Asynchronous stochastic approximation and Q-learning (context) - Tsitsiklis - 1993
48 Approximate dynamic programming for real-time control and ne.. (context) - Werbos - 1992
32 converges with probability - Dayan, Sejnowski - 1993
25 The convergence of TD (context) - Dayan - 1992
23 Sequential decision problems and neural networks (context) - Barto, Sutton et al. - 1990
12 On stochastic approximation (context) - Dvoretzky - 1956
9 A stochastic approximation model (context) - Robbins, Monro - 1951
7 Optimization of Stochastic Systems (context) - Aoki - 1967
4 Department of Computer Science preprint (context) - Peng, Williams - 1993
Documents on the same site (http://www.cs.berkeley.edu/~jordan/publications.html): More
Improving the Mean Field Approximation via the Use of.. - Jaakkola, Jordan (1998) (Correct)
Variational probabilistic inference and the QMR-DT database - Jaakkola, Jordan (1998) (Correct)
Hidden Markov decision trees - Jordan, Ghahramani, Saul (1997) (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