Sciweavers

113 search results - page 8 / 23
» Learning Representation and Control in Continuous Markov Dec...
Sort
View
COLT
2000
Springer
14 years 1 months ago
Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process (  ¢¡¤£¦¥§  ), and focus on gradient ascent approache...
Peter L. Bartlett, Jonathan Baxter
CORR
2012
Springer
235views Education» more  CORR 2012»
12 years 4 months ago
An Incremental Sampling-based Algorithm for Stochastic Optimal Control
Abstract— In this paper, we consider a class of continuoustime, continuous-space stochastic optimal control problems. Building upon recent advances in Markov chain approximation ...
Vu Anh Huynh, Sertac Karaman, Emilio Frazzoli
ICRA
2007
IEEE
126views Robotics» more  ICRA 2007»
14 years 3 months ago
A formal framework for robot learning and control under model uncertainty
— While the Partially Observable Markov Decision Process (POMDP) provides a formal framework for the problem of robot control under uncertainty, it typically assumes a known and ...
Robin Jaulmes, Joelle Pineau, Doina Precup
GECCO
2005
Springer
130views Optimization» more  GECCO 2005»
14 years 2 months ago
ATNoSFERES revisited
ATNoSFERES is a Pittsburgh style Learning Classifier System (LCS) in which the rules are represented as edges of an Augmented Transition Network. Genotypes are strings of tokens ...
Samuel Landau, Olivier Sigaud, Marc Schoenauer
NIPS
2007
13 years 10 months ago
Online Linear Regression and Its Application to Model-Based Reinforcement Learning
We provide a provably efficient algorithm for learning Markov Decision Processes (MDPs) with continuous state and action spaces in the online setting. Specifically, we take a mo...
Alexander L. Strehl, Michael L. Littman