Sciweavers

378 search results - page 7 / 76
» Evolutionary Learning Strategy using Bug-Based Search
Sort
View
IWCLS
2007
Springer
14 years 1 months ago
On Lookahead and Latent Learning in Simple LCS
Learning Classifier Systems use evolutionary algorithms to facilitate rule- discovery, where rule fitness is traditionally payoff based and assigned under a sharing scheme. Most c...
Larry Bull
GECCO
2009
Springer
162views Optimization» more  GECCO 2009»
13 years 5 months ago
Uncertainty handling CMA-ES for reinforcement learning
The covariance matrix adaptation evolution strategy (CMAES) has proven to be a powerful method for reinforcement learning (RL). Recently, the CMA-ES has been augmented with an ada...
Verena Heidrich-Meisner, Christian Igel
ECML
2004
Springer
14 years 22 days ago
Analyzing Multi-agent Reinforcement Learning Using Evolutionary Dynamics
In this paper, we show how the dynamics of Q-learning can be visualized and analyzed from a perspective of Evolutionary Dynamics (ED). More specifically, we show how ED can be use...
Pieter Jan't Hoen, Karl Tuyls
SAC
2009
ACM
14 years 2 months ago
A gradient oriented recombination scheme for evolution strategies
This paper proposes a novel recombination scheme for evolutionary algorithms, which can guide the new population generation towards the maximum increase of the objective function....
Haifeng Chen, Guofei Jiang
PPSN
2004
Springer
14 years 21 days ago
A Primer on the Evolution of Equivalence Classes of Bayesian-Network Structures
Bayesian networks (BN) constitute a useful tool to model the joint distribution of a set of random variables of interest. To deal with the problem of learning sensible BN models fr...
Jorge Muruzábal, Carlos Cotta