Sciweavers

51 search results - page 7 / 11
» Characterizing reinforcement learning methods through parame...
Sort
View
GECCO
2008
Springer
128views Optimization» more  GECCO 2008»
13 years 8 months ago
Adapted Pittsburgh classifier system: building accurate strategies in non markovian environments
This paper focuses on the study of the behavior of a genetic algorithm based classifier system, the Adapted Pittsburgh Classifier System (A.P.C.S), on maze type environments con...
Gilles Énée, Mathias Péroumal...
CI
2005
106views more  CI 2005»
13 years 7 months ago
Incremental Learning of Procedural Planning Knowledge in Challenging Environments
Autonomous agents that learn about their environment can be divided into two broad classes. One class of existing learners, reinforcement learners, typically employ weak learning ...
Douglas J. Pearson, John E. Laird
ATAL
2003
Springer
14 years 26 days ago
Resource allocation games with changing resource capacities
In this paper we study a class of resource allocation games which are inspired by the El Farol Bar problem. We consider a system of competitive agents that have to choose between ...
Aram Galstyan, Shashikiran Kolar, Kristina Lerman
PKDD
2010
Springer
164views Data Mining» more  PKDD 2010»
13 years 5 months ago
Efficient Planning in Large POMDPs through Policy Graph Based Factorized Approximations
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...
Joni Pajarinen, Jaakko Peltonen, Ari Hottinen, Mik...
ECML
2007
Springer
14 years 1 months ago
Policy Gradient Critics
We present Policy Gradient Actor-Critic (PGAC), a new model-free Reinforcement Learning (RL) method for creating limited-memory stochastic policies for Partially Observable Markov ...
Daan Wierstra, Jürgen Schmidhuber