754 search results - page 57 / 151 » Learning executable agent behaviors from observation |
196
click to vote
Publication
We state the problem of inverse reinforcement learning in terms of preference elicitation, resulting in a principled (Bayesian) statistical formulation. This generalises previous w...
144
Voted
LAMAS
2005
Springer
15 years 10 months ago
2005
Springer
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...
183
click to vote
Publication
New cameras are installed daily all around the world. Hence it becomes increasingly important to develop methods for reducing the manual effort that is still required for video ana...
133
click to vote
CHI
2006
ACM
16 years 4 months ago
2006
ACM
Digital Manipulatives embed computation in familiar children's toys and provide means for children to design behavior. Some systems use "record and play" as a form ...
135
click to vote
CORR
2007
Springer
15 years 4 months ago
2007
Springer
—We consider an agent interacting with an unmodeled environment. At each time, the agent makes an observation, takes an action, and incurs a cost. Its actions can influence futu...