Sciweavers

892 search results - page 88 / 179
» Action respecting embedding
Sort
View
NIPS
2008
13 years 11 months ago
Particle Filter-based Policy Gradient in POMDPs
Our setting is a Partially Observable Markov Decision Process with continuous state, observation and action spaces. Decisions are based on a Particle Filter for estimating the bel...
Pierre-Arnaud Coquelin, Romain Deguest, Rém...
NAACL
2007
13 years 11 months ago
Incremental Non-Projective Dependency Parsing
An open issue in data-driven dependency parsing is how to handle non-projective dependencies, which seem to be required by linguistically adequate representations, but which pose ...
Joakim Nivre
AIPS
2003
13 years 11 months ago
A Mixed-initiative Framework for Robust Plan Sketching
Sketching provides a natural and compact means for a user to outline a plan for a high-level objective. Previous work on plan sketching required that sketches be valid, meaning th...
Karen L. Myers, Peter Jarvis, Mabry Tyson, Michael...
ATAL
2010
Springer
13 years 11 months ago
TacTex09: a champion bidding agent for ad auctions
In the Trading Agent Competition Ad Auctions Game, agents compete to sell products by bidding to have their ads shown in a search engine's sponsored search results. We report...
David Pardoe, Doran Chakraborty, Peter Stone
CORR
2008
Springer
147views Education» more  CORR 2008»
13 years 10 months ago
A Minimum Relative Entropy Principle for Learning and Acting
This paper proposes a method to construct an adaptive agent that is universal with respect to a given class of experts, where each expert is designed specifically for a particular...
Pedro A. Ortega, Daniel A. Braun