Shalabh Bhatnagar, Vivek S. Borkar, et al.  Home/Search
Context
Related
| jmlr.org/papers/volu...bhatnagar06a.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/papers/v7/ (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: We study the problem of long-run average cost control of Markov chains conditioned on a rare event. In a related recent work, a simulation based algorithm for estimating performance measures associated with a Markov chain conditioned on a rare event has been developed. We extend ideas from this work and develop an adaptive algorithm for obtaining, online, optimal control policies conditioned on a rare event. Our algorithm uses three timescales or step-size schedules. On the slowest... (Update)
Active bibliography (related documents): More All
1.1: Randomized Difference Two-Timescale Simultaneous.. - Bhatnagar, Fu, al. (2000) (Correct)
0.5: Convergence of Simulation-Based Policy Iteration - Cooper, Henderson, Lewis (2003) (Correct)
0.3: Optimal Multilevel Feedback Policies for ABR Flow Control.. - Bhatnagar, Fu, al. (1999) (Correct)
Similar documents based on text:
6.0: Unknown - (Correct)
BibTeX entry: (Update)
@misc{ bhatnagar-simulationbased,
author = "Shalabh Bhatnagar and Vivek S. Borkar and et al.",
title = "A Simulation-Based Algorithm for Ergodic Control of Markov Chains Conditioned
on Rare Events",
url = "citeseer.ist.psu.edu/bhatnagar06simulationbased.html" }
Citations (may not include all citations):614 Reinforcement Learning: An Introduction - Sutton, Barto - 1998
413 Neuro-dynamic Programming (context) - Bertsekas, Tsitsiklis - 1996
291 Simulation Modeling and Analysis (context) - Law, Kelton - 2000
281 Machine Learning (context) - Watkins, Dayan - 1992
278 Dynamic Programming and Optimal Control (context) - Bertsekas - 2001
120 Large Deviations Techniques in Decision (context) - Bucklew - 1990
50 Simulation-based optimization of markov reward processes - Marbach, Tsitsiklis - 2001
27 Multivariate stochastic approximation using a simultaneous p.. - Spall - 1992
26 Stochastic approximation with two timescales (context) - Borkar - 1997
21 Call admission control and routing in integrated services ne.. - Marbach, Mihatsch et al. - 2000
19 Distributed asynchronous optimal routing in data networks (context) - Tsitsiklis, Bertsekas - 1986
17 Stochastic optimization of regenerative systems using infini.. (context) - Chong, Ramadge - 1994
16 Asynchronous stochastic approximations - Borkar - 1998
15 Infinite-horizon policy-gradient estimation - Baxter, Bartlett - 2001
12 Spectral theory and limit theorems for geometrically ergodic.. - Kontoyiannis, Meyn - 2003
10 Multiplicative ergodicity and large deviations for an irredu.. - Balaji, Meyn - 2000
8 Actor-critic like learning algorithms for markov decision pr.. (context) - Konda, Borkar - 1999
7 Experiments with infinite-horizon (context) - Baxter, Bartlett et al. - 2001
6 Optimization of computer simulation models with rare events - Rubinstein - 1997
4 Multiscale stochastic approximation for parametric optimizat.. (context) - Bhatnagar, Borkar - 1997
4 A one-measurement form of simultaneous perturbation stochast.. (context) - Spall - 1997
4 Perturbation Analysis of Discrete Event Dynamical Systems (context) - Ho, Cao - 1991
3 Risk sensitive control of markov processes in countable stat.. (context) - andez-Hern, Marcus - 1996
2 A two time scale stochastic approximation scheme for simulat.. (context) - Bhatnagar, Borkar - 1998
2 A unified approach to markov decision problems and performan.. (context) - Cao, Guo - 2004
1 Adaptive importance sampling technique for markov chains usi.. (context) - Ahamed, Borkar et al. - 2006
1 Two timescale algorithms for simulation optimization of hidd.. (context) - Bhatnagar, Fu et al. - 2001
1 A sensitivity formula for risk-sensitive cost and the actor-.. (context) - Borkar - 2001
1 Two-timescale simultaneous perturbation stochastic approxima.. (context) - Bhatnagar, Fu et al. - 2003
1 A simultaneous perturbation stochastic approximation based a.. (context) - Bhatnagar, Kumar - 2004
1 learning for risk-sensitive control (context) - Borkar - 2002
1 learning for adaptive load based routing (context) - Nowe, Steenhaut et al. - 1994
1 Avoidance of traps in stochastic approximation (context) - Borkar - 2003
1 Reinforcing reachable routes - Varadarajan, Ramakrishnan et al. - 2003
1 Performance analysis conditioned on rare events: an adaptive.. (context) - Borkar, Juneja et al. - 2004
1 Some pathological traps for stochastic approximation (context) - Brandiere - 1998
1 Risk-sensitive optimal control for markov decision processes.. (context) - Borkar, Meyn - 2002
1 Adaptive multivariate three-timescale stochastic approximati.. (context) - Bhatnagar - 2005
1 Discrete Event Dynamic Systems (context) - Cao, among et al. - 1998
Documents on the same site (http://jmlr.csail.mit.edu/papers/v7/): More
Estimating the "Wrong" Graphical Model: Benefits in the.. - Wainwright (2006) (Correct)
A Hierarchy of Support Vector Machines for Pattern Detection - Sahbi, Geman (2006) (Correct)
Efficient Learning of Label Ranking by Soft Projections.. - Shalev-Shwartz, Singer (2006) (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