Search Sciweavers | Sciweavers

223 search results - page 10 / 45

» Least-Squares Temporal Difference Learning

click to vote

ICML
2003
IEEE

168views Machine Learning» more ICML 2003»

Bayes Meets Bellman: The Gaussian Process Approach to Temporal Difference Learning

14 years 9 months ago

Download webee.technion.ac.il

We present a novel Bayesian approach to the problem of value function estimation in continuous state spaces. We define a probabilistic generative model for the value function by i...

Yaakov Engel, Shie Mannor, Ron Meir

claim paper

Read More »

click to vote

ML
2000
ACM

126views Machine Learning» more ML 2000»

Learning to Play Chess Using Temporal Differences

13 years 8 months ago

Download www.cs.princeton.edu

In this paper we present TDLEAF( ), a variation on the TD( ) algorithm that enables it to be used in conjunction with game-tree search. We present some experiments in which our che...

Jonathan Baxter, Andrew Tridgell, Lex Weaver

claim paper

Read More »

click to vote

ISDA
2009
IEEE

144views Operating System» more ISDA 2009»

Postponed Updates for Temporal-Difference Reinforcement Learning

14 years 3 months ago

Download www.science.uva.nl

This paper presents postponed updates, a new strategy for TD methods that can improve sample efﬁciency without incurring the computational and space requirements of model-based ...

Harm van Seijen, Shimon Whiteson

claim paper

Read More »

click to vote

AAMAS
2010
Springer

190views Intelligent Agents» more AAMAS 2010»

Critical factors in the empirical performance of temporal difference and evolutionary methods for reinforcement learning

13 years 8 months ago