Sciweavers

718 search results - page 90 / 144
» On Defaults in Action Theories
Sort
View
IROS
2008
IEEE
125views Robotics» more  IROS 2008»
15 years 4 months ago
Dynamic correlation matrix based multi-Q learning for a multi-robot system
—Multi-robot reinforcement learning is a very challenging area due to several issues, such as large state spaces, difficulty in reward assignment, nondeterministic action selecti...
Hongliang Guo, Yan Meng
ATAL
2007
Springer
15 years 4 months ago
Towards collaborative task and team maintenance
There is significant interest in modeling teamwork in agents. In recent years, it has become widely accepted that it is possible to separate teamwork from taskwork, providing sup...
Gal A. Kaminka, Ari Yakir, Dan Erusalimchik, Nirom...
UM
2007
Springer
15 years 3 months ago
Inducing User Affect Recognition Models for Task-Oriented Environments
Accurately recognizing users’ affective states could contribute to more productive and enjoyable interactions, particularly for task-oriented learning environments. In addition t...
Sunyoung Lee, Scott W. McQuiggan, James C. Lester
ICTAI
2005
IEEE
15 years 3 months ago
Planning with POMDPs Using a Compact, Logic-Based Representation
Partially Observable Markov Decision Processes (POMDPs) provide a general framework for AI planning, but they lack the structure for representing real world planning problems in a...
Chenggang Wang, James G. Schmolze
ROBOCUP
2005
Springer
109views Robotics» more  ROBOCUP 2005»
15 years 3 months ago
Using the Max-Plus Algorithm for Multiagent Decision Making in Coordination Graphs
Abstract. Coordination graphs offer a tractable framework for cooperative multiagent decision making by decomposing the global payoff function into a sum of local terms. Each age...
Jelle R. Kok, Nikos A. Vlassis