Sciweavers

Share
38 search results - page 1 / 8
» Improving reinforcement learning function approximators via ...
Sort
View
ATAL
2005
Springer
9 years 11 months ago
Improving reinforcement learning function approximators via neuroevolution
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
Shimon Whiteson
AAAI
2006
9 years 7 months ago
Sample-Efficient Evolutionary Function Approximation for Reinforcement Learning
Reinforcement learning problems are commonly tackled with temporal difference methods, which attempt to estimate the agent's optimal value function. In most real-world proble...
Shimon Whiteson, Peter Stone
ICML
2007
IEEE
10 years 6 months ago
Tracking value function dynamics to improve reinforcement learning with piecewise linear function approximation
Reinforcement learning algorithms can become unstable when combined with linear function approximation. Algorithms that minimize the mean-square Bellman error are guaranteed to co...
Chee Wee Phua, Robert Fitch
IROS
2007
IEEE
168views Robotics» more  IROS 2007»
9 years 12 months ago
Improving humanoid locomotive performance with learnt approximated dynamics via Gaussian processes for regression
Abstract— We propose to improve the locomotive performance of humanoid robots by using approximated biped stepping and walking dynamics with reinforcement learning (RL). Although...
Jun Morimoto, Christopher G. Atkeson, Gen Endo, Go...
GECCO
2004
Springer
122views Optimization» more  GECCO 2004»
9 years 11 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
books