Sciweavers

1174 search results - page 115 / 235
» Functional Trees
Sort
View
CG
2006
Springer
15 years 4 months ago
Feature Construction for Reinforcement Learning in Hearts
Temporal difference (TD) learning has been used to learn strong evaluation functions in a variety of two-player games. TD-gammon illustrated how the combination of game tree search...
Nathan R. Sturtevant, Adam M. White
ECML
2007
Springer
15 years 8 months ago
Transfer Learning in Reinforcement Learning Problems Through Partial Policy Recycling
In this paper we investigate the relation between transfer learning in reinforcement learning with function approximation and supervised learning with concept drift. We present a n...
Jan Ramon, Kurt Driessens, Tom Croonenborghs
111
Voted
AAAI
2011
14 years 2 months ago
Optimal Rewards versus Leaf-Evaluation Heuristics in Planning Agents
Planning agents often lack the computational resources needed to build full planning trees for their environments. Agent designers commonly overcome this finite-horizon approxima...
Jonathan Sorg, Satinder P. Singh, Richard L. Lewis
CEC
2011
IEEE
14 years 2 months ago
Cost-benefit analysis of using heuristics in ACGP
—Constrained Genetic Programming (CGP) is a method of searching the Genetic Programming search space non-uniformly, giving preferences to certain subspaces according to some heur...
John W. Aleshunas, Cezary Z. Janikow
135
Voted
BMCBI
2002
126views more  BMCBI 2002»
15 years 2 months ago
RIO: Analyzing proteomes by automated phylogenomics using resampled inference of orthologs
Background: When analyzing protein sequences using sequence similarity searches, orthologous sequences (that diverged by speciation) are more reliable predictors of a new protein&...
Christian M. Zmasek, Sean R. Eddy