272 search results - page 35 / 55 » Parallel Reinforcement Learning with Linear Function Approxi... |
GECCO
2006
Springer
13 years 11 months ago
2006
Springer
XCSF is a novel version of learning classifier systems (LCS) which extends the typical concept of LCS by introducing computable classifier prediction. In XCSF Classifier predictio...
NIPS
2001
13 years 9 months ago
2001
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
ML
2002
ACM
13 years 7 months ago
2002
ACM
We provide an analytical comparison between discounted and average reward temporal-difference (TD) learning with linearly parameterized approximations. We first consider the asympt...
IPPS
2009
IEEE
14 years 2 months ago
2009
IEEE
We are interested in this paper to study scheduling problems in systems where many users compete to perform their respective jobs on shared parallel resources. Each user has speci...
PKDD
2010
Springer
13 years 5 months ago
2010
Springer
Abstract. We present a novel approach for classification using a discretised function representation which is independent of the data locations. We construct the classifier as a su...