2440 search results - page 193 / 488 » Learn .MT: A New Approach to Incremental Learning |
153
click to vote
EMNLP
2007
15 years 8 months ago
2007
We consider the problem of learning to parse sentences to lambda-calculus representations of their underlying semantics and present an algorithm that learns a weighted combinatory...
162
click to vote
IJCAI
2007
15 years 8 months ago
2007
Machine learning for predicting user clicks in Webbased search offers automated explanation of user activity. We address click prediction in the Web search scenario by introducing...
170
click to vote
IJCAI
2003
15 years 8 months ago
2003
We present a new algorithm, GM-Sarsa(0), for finding approximate solutions to multiple-goal reinforcement learning problems that are modeled as composite Markov decision processe...
186
click to vote
JAIR
2002
15 years 6 months ago
2002
Designing the dialogue policy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing a di...
169
click to vote
ML
2002
ACM
15 years 6 months ago
2002
ACM
We present new algorithms for reinforcement learning, and prove that they have polynomial bounds on the resources required to achieve near-optimal return in general Markov decisio...