Sciweavers

495 search results - page 1 / 99
» Constructing States for Reinforcement Learning
Sort
View
ICML
2010
IEEE
13 years 1 months ago
Constructing States for Reinforcement Learning
POMDPs are the models of choice for reinforcement learning (RL) tasks where the environment cannot be observed directly. In many applications we need to learn the POMDP structure ...
M. M. Hassan Mahmud
ICML
2006
IEEE
13 years 9 months ago
Automatic basis function construction for approximate dynamic programming and reinforcement learning
We address the problem of automatically constructing basis functions for linear approximation of the value function of a Markov Decision Process (MDP). Our work builds on results ...
Philipp W. Keller, Shie Mannor, Doina Precup
CG
2006
Springer
13 years 5 months ago
Feature Construction for Reinforcement Learning in Hearts
Temporal difference (TD) learning has been used to learn strong evaluation functions in a variety of two-player games. TD-gammon illustrated how the combination of game tree search...
Nathan R. Sturtevant, Adam M. White
EACL
2006
ACL Anthology
13 years 5 months ago
Using Reinforcement Learning to Build a Better Model of Dialogue State
Given the growing complexity of tasks that spoken dialogue systems are trying to handle, Reinforcement Learning (RL) has been increasingly used as a way of automatically learning ...
Joel R. Tetreault, Diane J. Litman
FLAIRS
2004
13 years 5 months ago
State Space Reduction For Hierarchical Reinforcement Learning
er provides new techniques for abstracting the state space of a Markov Decision Process (MDP). These techniques extend one of the recent minimization models, known as -reduction, ...
Mehran Asadi, Manfred Huber