181 search results - page 8 / 37 » On Policy Learning in Restricted Policy Spaces |
ICMLA
2010
13 years 5 months ago
2010
Abstract-- Policy Gradients with Parameter-based Exploration (PGPE) is a novel model-free reinforcement learning method that alleviates the problem of high-variance gradient estima...
Publication
Abstract: Several approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervis...
ATAL
2007
Springer
14 years 1 months ago
2007
Springer
The ambitious goal of transfer learning is to accelerate learning on a target task after training on a different, but related, source task. While many past transfer methods have f...
GLOBECOM
2006
IEEE
14 years 1 months ago
2006
IEEE
— This paper addresses learning based adaptive resource allocation for wireless MIMO channels with Markovian fading. The problem is posed as Constrained Markov Decision Process w...
PKDD
2010
Springer
13 years 5 months ago
2010
Springer
Partially observable Markov decision processes (POMDPs) are widely used for planning under uncertainty. In many applications, the huge size of the POMDP state space makes straightf...