Sciweavers

1512 search results - page 15 / 303
» Qualitative reinforcement learning
Sort
View
GECCO
2004
Springer
122views Optimization» more  GECCO 2004»
14 years 1 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