Sciweavers

3729 search results - page 681 / 746
» On Formal Modeling of Agent Computations
Sort
View
157
Voted
IJCAI
2003
15 years 7 months ago
Generalizing Plans to New Environments in Relational MDPs
A longstanding goal in planning research is the ability to generalize plans developed for some set of environments to a new but similar environment, with minimal or no replanning....
Carlos Guestrin, Daphne Koller, Chris Gearhart, Ne...
219
Voted
AIIDE
2009
15 years 7 months ago
Examining Extended Dynamic Scripting in a Tactical Game Framework
Dynamic scripting is a reinforcement learning algorithm designed specifically to learn appropriate tactics for an agent in a modern computer game, such as Neverwinter Nights. This...
Jeremy Ludwig, Arthur Farley
PAMI
2010
162views more  PAMI 2010»
15 years 26 days ago
Differential Earth Mover's Distance with Its Applications to Visual Tracking
The Earth Mover's Distance (EMD) is a similarity measure that captures perceptual difference between two distributions. Its computational complexity, however, prevents a direc...
Qi Zhao, Zhi Yang, Hai Tao
ACL
2011
14 years 9 months ago
Learning to Win by Reading Manuals in a Monte-Carlo Framework
This paper presents a novel approach for leveraging automatically extracted textual knowledge to improve the performance of control applications such as games. Our ultimate goal i...
S. R. K. Branavan, David Silver, Regina Barzilay
CVPR
2012
IEEE
13 years 8 months ago
Social behavior recognition in continuous video
We present a novel method for analyzing social behavior. Continuous videos are segmented into action ‘bouts’ by building a temporal context model that combines features from s...
Xavier P. Burgos-Artizzu, Piotr Dollár, Day...