Sciweavers

878 search results - page 95 / 176
» Learning to Control in Operational Space
Sort
View
AAAI
2011
14 years 4 months ago
Combining Learned Discrete and Continuous Action Models
Action modeling is an important skill for agents that must perform tasks in novel domains. Previous work on action modeling has focused on learning STRIPS operators in discrete, r...
Joseph Z. Xu, John E. Laird
124
Voted
ICCBR
2009
Springer
15 years 10 months ago
An Active Approach to Automatic Case Generation
Abstract. When learning by observing an expert, cases can be automatically generated in an inexpensive manner. However, since this is a passive method of learning the observer has ...
Michael W. Floyd, Babak Esfandiari
135
Voted
ICCS
1993
Springer
15 years 8 months ago
Towards Domain-Independent Machine Intelligence
Adaptive predictive search (APS), is a learning system framework, which given little initial domain knowledge, increases its decision-making abilities in complex problems domains....
Robert Levinson
EPIA
1995
Springer
15 years 7 months ago
Using Stochastic Grammars to Learn Robotic Tasks
Abstract. The paper introduces a reinforcement learning-based methodology for performance improvement of Intelligent Controllers. The translation interfaces of a 3-level Hierarchic...
Pedro U. Lima, George N. Saridis
ICRA
2005
IEEE
137views Robotics» more  ICRA 2005»
15 years 9 months ago
Learning Opportunity Costs in Multi-Robot Market Based Planners
— Direct human control of multi-robot systems is limited by the cognitive ability of humans to coordinate numerous interacting components. In remote environments, such as those e...
Jeff G. Schneider, David Apfelbaum, Drew Bagnell, ...