Sciweavers

2011 search results - page 5 / 403

» Universal Reinforcement Learning

19

ICML
1998
IEEE

152views Machine Learning» more ICML 1998»

Multi-criteria Reinforcement Learning

14 years 8 months ago

Multi-criteria Reinforcement Learning

Download www.cs.rpi.edu

Csaba Szepesvári, Zoltán Gábo...

claim paper

Read More »

19

ICML
1998
IEEE

149views Machine Learning» more ICML 1998»

An Analysis of Direct Reinforcement Learning in Non-Markovian Domains

14 years 8 months ago

An Analysis of Direct Reinforcement Learning in Non-Markovian Domains

Download staff.uqu.edu.sa

Mark D. Pendrith, Michael McGarity

claim paper

Read More »

19

ICML
1996
IEEE

126views Machine Learning» more ICML 1996»

On-Line Adaptation of a Signal Predistorter through Dual Reinforcement Learning

14 years 8 months ago

On-Line Adaptation of a Signal Predistorter through Dual Reinforcement Learning

Download www.cs.utexas.edu

Patrick Goetz, Shailesh Kumar, Risto Miikkulainen

claim paper

Read More »

20

CORR
1998
Springer

164views Education» more CORR 1998»

Training Reinforcement Neurocontrollers Using the Polytope Algorithm

13 years 6 months ago

Training Reinforcement Neurocontrollers Using the Polytope Algorithm

Download zeus.cs.uoi.gr

A new training algorithm is presented for delayed reinforcement learning problems that does not assume the existence of a critic model and employs the polytope optimization algorit...

Aristidis Likas, Isaac E. Lagaris

claim paper

Read More »

19

ESANN
2006

114views Neural Networks» more ESANN 2006»

Reducing policy degradation in neuro-dynamic programming

13 years 8 months ago

Reducing policy degradation in neuro-dynamic programming

Download ml.informatik.uni-freiburg.de

We focus on neuro-dynamic programming methods to learn state-action value functions and outline some of the inherent problems to be faced, when performing reinforcement learning in...

Thomas Gabel, Martin Riedmiller

claim paper

Read More »

« Prev « First page 5 / 403 Last » Next »