1056 search results - page 139 / 212 » ijcai 2007 |
148
click to vote
IJCAI
2007
15 years 7 months ago
2007
A long-lived agent continually faces new tasks in its environment. Such an agent may be able to use knowledge learned in solving earlier tasks to produce candidate policies for it...
162
click to vote
IJCAI
2007
15 years 7 months ago
2007
Markov Decision Processes are a powerful framework for planning under uncertainty, but current algorithms have difficulties scaling to large problems. We present a novel probabil...
166
click to vote
IJCAI
2007
15 years 7 months ago
2007
This article proposes a Diagnosis Interchange Format (DIF), an XML-based interchange format for Model-Based Diagnosis (MBD). Its main purposes are to allow sharing of diagnostic m...
150
click to vote
IJCAI
2007
15 years 7 months ago
2007
In the past ten years, boosting has become a major field of machine learning and classification. This paper brings contributions to its theory and algorithms. We first unify a ...
128
click to vote
IJCAI
2007
15 years 7 months ago
2007
Although necessary, learning to discover new solutions is often long and difficult, even for supposedly simple tasks such as counting. On the other hand, learning by imitation pr...