Sciweavers

425 search results - page 64 / 85
» Metacognitive Control and Optimal Learning
Sort
View
CP
2000
Springer
15 years 2 months ago
Constraint-Based Agents: The ABC's of CBA's
The Constraint-Based Agent (CBA) framework is a set of tools for designing, simulating, building, verifying, optimizing, learning and debugging controllers for agents embedded in a...
Alan K. Mackworth
FLAIRS
2003
14 years 11 months ago
Cost-Based Policy Mapping for Imitation
Imitation represents a powerful approach for programming and autonomous learning in robot and computer systems. An important aspect of imitation is the mapping of observations to ...
Srichandan V. Gudla, Manfred Huber
ICML
2006
IEEE
15 years 10 months ago
Probabilistic inference for solving discrete and continuous state Markov Decision Processes
Inference in Markov Decision Processes has recently received interest as a means to infer goals of an observed action, policy recognition, and also as a tool to compute policies. ...
Marc Toussaint, Amos J. Storkey
GECCO
2007
Springer
177views Optimization» more  GECCO 2007»
15 years 3 months ago
Evolving problem heuristics with on-line ACGP
Genetic Programming uses trees to represent chromosomes. The user defines the representation space by defining the set of functions and terminals to label the nodes in the trees. ...
Cezary Z. Janikow
GECCO
2007
Springer
171views Optimization» more  GECCO 2007»
15 years 3 months ago
Toward a better understanding of rule initialisation and deletion
A number of heuristics have been used in Learning Classifier Systems to initialise parameters of new rules, to adjust fitness of parent rules when they generate offspring, and ...
Tim Kovacs, Larry Bull