3505 search results - page 205 / 701 » A Language for Human Action |
222
click to vote
JMLR
2012
13 years 9 months ago
2012
Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on th...
156
click to vote
HICSS
2006
IEEE
16 years 20 days ago
2006
IEEE
We report on the effectiveness of language models for personalization of retrieval results based on a searcher’s preference for document genre. In principle, such preferences ca...
150
click to vote
ICALP
2003
Springer
15 years 12 months ago
2003
Springer
We provide an answer to an open question, posed by van Glabbeek [4], regarding the axiomatizability of ready trace semantics. We prove that if the alphabet of actions is finite, t...
148
click to vote
KI
1997
Springer
15 years 10 months ago
1997
Springer
Abstract. Agents situated in proactive environments are acting autonomously while the environment is evolving alongside, whether or not the agents carry out any particular actions....
210
click to vote
ACL
1997
15 years 8 months ago
1997
We present a knowledge and context-based system for parsing and translating natural language and evaluate it on sentences from the Wall Street Journal. Applying machine learning t...