5945 search results - page 260 / 1189 » A Model for Projection and Action |
185
click to vote
COLT
2006
Springer
15 years 10 months ago
2006
Springer
We consider online learning in repeated decision problems, within the framework of a repeated game against an arbitrary opponent. For repeated matrix games, well known results esta...
186
click to vote
AAAI
1998
15 years 8 months ago
1998
We present a technique for computing approximately optimal solutions to stochastic resource allocation problems modeled as Markov decision processes (MDPs). We exploit two key pro...
213
click to vote
COMPLEXITY
2007
15 years 6 months ago
2007
: Conflict is a dynamic and complex form of human interaction, often emerging from incompatible actions, values and goals, and consuming a considerable amount of resources. Conflic...
231
click to vote
TROB
2010
15 years 1 months ago
2010
Abstract--Acquisition of new sensorimotor knowledge by imitation is a promising paradigm for robot learning. To be effective, action learning should not be limited to direct replic...
150
click to vote
CHI
2005
ACM
16 years 7 months ago
2005
ACM
We describe a technique that supports the previewing of navigation, exploration, and editing operations by providing convenient Undo for unsuccessful and/or undesirable actions on...