Sciweavers

536 search results - page 21 / 108
» Residual Algorithms: Reinforcement Learning with Function Ap...
Sort
View
PKDD
2009
Springer
169views Data Mining» more  PKDD 2009»
14 years 2 months ago
Hybrid Least-Squares Algorithms for Approximate Policy Evaluation
The goal of approximate policy evaluation is to “best” represent a target value function according to a specific criterion. Temporal difference methods and Bellman residual m...
Jeffrey Johns, Marek Petrik, Sridhar Mahadevan
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
AIPS
2008
13 years 10 months ago
Learning Heuristic Functions through Approximate Linear Programming
Planning problems are often formulated as heuristic search. The choice of the heuristic function plays a significant role in the performance of planning systems, but a good heuris...
Marek Petrik, Shlomo Zilberstein
BIOINFORMATICS
2007
151views more  BIOINFORMATICS 2007»
13 years 7 months ago
A new protein-protein docking scoring function based on interface residue properties
Motivation: Protein–protein complexes are known to play key roles in many cellular processes. However, they are often not accessible to experimental study because of their low s...
Julie Bernauer, Jérôme Azé, Jo...
ICML
1998
IEEE
14 years 8 months ago
The MAXQ Method for Hierarchical Reinforcement Learning
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
Thomas G. Dietterich