Sciweavers

1270 search results - page 205 / 254
» Dogged Learning for Robots
Sort
View
IJCAI
1989
14 years 11 months ago
Selective Learning of Macro-operators with Perfect Causality
A macro-operator is an integrated operator consisting of plural primitive operators and enables a problem solver to solve more efficiently. However, if a learning system generates...
Seiji Yamada, Sabinro Tsuji
AAAI
2011
13 years 9 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
ICML
1995
IEEE
15 years 10 months ago
Learning Policies for Partially Observable Environments: Scaling Up
Partially observable Markov decision processes (pomdp's) model decision problems in which an agent tries to maximize its reward in the face of limited and/or noisy sensor fee...
Michael L. Littman, Anthony R. Cassandra, Leslie P...
CDC
2008
IEEE
113views Control Systems» more  CDC 2008»
15 years 4 months ago
Norm optimal Cross-Coupled Iterative Learning Control
— In this paper, we focus on improving contour tracking in precision motion control (PMC) applications through the use of Cross-Coupled Iterative Learning Control (CCILC). Initia...
Kira Barton, Jeroen van de Wijdeven, Andrew Alleyn...
ICALT
2006
IEEE
15 years 3 months ago
Instruction Through The Ages: Building Pervasive Virtual Instructors for Life Long Learning
A pervasive virtual instructor is an artificially intelligent instructor that may appear transparent to the learner or appear in the form of a threedimensional graphical character...
Jayfus T. Doswell