Sciweavers

250 search results - page 7 / 50
» Learning action effects in partially observable domains
Sort
View
ROBOCUP
2004
Springer
106views Robotics» more  ROBOCUP 2004»
15 years 2 months ago
Predicting Opponent Actions by Observation
In competitive domains, the knowledge about the opponent can give players a clear advantage. This idea lead us in the past to propose an approach to acquire models of opponents, ba...
Agapito Ledezma, Ricardo Aler, Araceli Sanch&iacut...
HICSS
2009
IEEE
94views Biometrics» more  HICSS 2009»
15 years 4 months ago
Enhancing Learning Experiences in Partially Distributed Teams: Training Students to Work Effectively Across Distances
Three training modules were designed to decrease ingroup dynamics in Partially Distributed Teams, which have two or more geographically separated subteams. The action research ori...
Rosalie J. Ocker, Dana Kracaw, Starr Roxanne Hiltz...
UAI
2000
14 years 11 months ago
Learning to Cooperate via Policy Search
Cooperative games are those in which both agents share the same payoff structure. Valuebased reinforcement-learning algorithms, such as variants of Q-learning, have been applied t...
Leonid Peshkin, Kee-Eung Kim, Nicolas Meuleau, Les...
AAAI
2010
14 years 11 months ago
PUMA: Planning Under Uncertainty with Macro-Actions
Planning in large, partially observable domains is challenging, especially when a long-horizon lookahead is necessary to obtain a good policy. Traditional POMDP planners that plan...
Ruijie He, Emma Brunskill, Nicholas Roy
LAMAS
2005
Springer
15 years 3 months ago
The Success and Failure of Tag-Mediated Evolution of Cooperation
Use of tags to limit partner selection for playing has been shown to produce stable cooperation in agent populations playing the Prisoner’s Dilemma game. There is, however, a lac...
Austin McDonald, Sandip Sen