http://www.merl.com Non-Linear Stochastic Control in Continuous State Spaces...  Home/Search
Context
Related
| merl.com/reports/docs/TR2003091.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: merl.com/reports/docs/ (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: We present an algorithm for sequential control of tasks with non-linear stochastic dynamics in continuous state spaces, characterized by inhomogeneous noise. The algorithm performs approximate value iteration steps on a select set of prototypical states whose cost-to-go is approximated by means of a radial-basis function network. This allows the resulting Bellman's equations to be integrated exactly with respect to the transition densities of a large class of stochastic dynamical systems,... (Update)
Active bibliography (related documents): More All
0.1: Learning State Grounding for Optimal Visual Servo Control.. - Nikovski, Nourbakhsh (2001) (Correct)
0.1: Reinforcement Learning with Policy Constraints - Thrun, Schulte (Correct)
0.1: Learning Probabilistic Models for Optimal Visual Servo.. - Nikovski, Nourbakhsh (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{ merl-mitsubishi,
author = "Http Www Merl",
title = "Mitsubishi Electric Research Laboratories",
url = "citeseer.ist.psu.edu/742369.html" }
Citations (may not include all citations):413 Neuro-Dynamic Programming (context) - Bertsekas, Tsitsiklis - 1996
291 Markov Decision Processes--- Discrete Stochastic Dynamic Pro.. (context) - Puterman - 1994
278 Dynamic Programming and Optimal Control (context) - Bertsekas - 2000
219 Practical issues in temporal difference learning - Tesauro - 1992
212 A probabilistic approach to concurrent mapping and localizat.. - Thrun, Burgard et al. - 1998
102 Generalization in reinforcement learning: Safely approximati.. - Boyan, Moore - 1995
74 Probabilistic algorithms in robotics - Thrun - 2000
61 Networks and the best approximation property - Girosi, Poggio - 1990
59 Feature-based methods for large scale dynamic programming - Tsitsiklis, van Roy - 1996
33 Optimal Control and Estimation (context) - Stengel - 1994
30 High-performance job-shop scheduling with a time-delay TD - Zhang, Dietterich - 1996
28 The swingup control problem for the acrobot (context) - Spong - 1995
24 Elevator group control using multiple reinforcement learning.. - Crites, Barto - 1998
9 Kernel-based reinforcement learning - Ormoneit, Sen - 1999
7 Stable fitted reinforcement learning - Gordon - 1996
7 Pole balancing on a real rig using a reinforcement learning .. (context) - Jervis, Fallside - 1992
Documents on the same site (http://www.merl.com/reports/docs/): More
Iterative Decoding Using Replicas - Zhang, Wang, Fossorier, Yedidia (2005) (Correct)
A Unified Traffic Control Scheme For Atm Networks.. - Zheng, Lauer, Howard.. (1994) (Correct)
Rapid Object Detection Using a Boosted Cascade of Simple Features - Viola, Jones (2004) (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