Sciweavers

1236 search results - page 31 / 248
» Opposition-Based Reinforcement Learning
Sort
View
EWRL
2008
15 years 2 months ago
Bayesian Reward Filtering
A wide variety of function approximation schemes have been applied to reinforcement learning. However, Bayesian filtering approaches, which have been shown efficient in other field...
Matthieu Geist, Olivier Pietquin, Gabriel Fricout
116
Voted
GECCO
2004
Springer
122views Optimization» more  GECCO 2004»
15 years 6 months ago
Gradient-Based Learning Updates Improve XCS Performance in Multistep Problems
This paper introduces a gradient-based reward prediction update mechanism to the XCS classifier system as applied in neuralnetwork type learning and function approximation mechani...
Martin V. Butz, David E. Goldberg, Pier Luca Lanzi
80
Voted
ICML
1997
IEEE
16 years 1 months ago
Exponentiated Gradient Methods for Reinforcement Learning
Doina Precup, Richard S. Sutton
89
Voted
ICML
2003
IEEE
15 years 6 months ago
Reinforcement Learning as Classification: Leveraging Modern Classifiers
Michail G. Lagoudakis, Ronald Parr