Sciweavers

1800 search results - page 209 / 360
» Learning Restart Strategies
Sort
View
AAAI
2010
15 years 4 months ago
Simultaneous Elicitation of Preference Features and Utility
Most frameworks for utility elicitation assume a predefined set of features over which user preferences are expressed. We consider utility elicitation in the presence of subjecti...
Craig Boutilier, Kevin Regan, Paolo Viappiani
IEEECIT
2010
IEEE
15 years 4 months ago
Application of Concept Maps-based Anchored Instruction in Programming Course
—In need of interesting material and effective teaching approach in programming learning, students were ely to drop out of the course for the abstract concepts and complex struct...
Liu Li, Haijun Mao, Licheng Xu
JMLR
2010
189views more  JMLR 2010»
15 years 19 days ago
Adaptive Step-size Policy Gradients with Average Reward Metric
In this paper, we propose a novel adaptive step-size approach for policy gradient reinforcement learning. A new metric is defined for policy gradients that measures the effect of ...
Takamitsu Matsubara, Tetsuro Morimura, Jun Morimot...
AIED
2009
Springer
16 years 13 days ago
Interactive Paraphrase Training: The Development and Testing of an iSTART Module
Comprehension of science texts is challenging, particularly when the reader lacks the skills or knowledge necessary to fill in conceptual gaps in the text content. The iSTART syste...
Danielle S. McNamara, Chutima Boonthum, Christophe...
DEXA
2004
Springer
159views Database» more  DEXA 2004»
15 years 9 months ago
Adaptive Double Routing Indices: Combining Effectiveness and Efficiency in P2P Systems
Unstructured peer-to-peer systems rely on strategies and data structures (Routing Indices) for the routing of requests in the network. For those requests corresponding to informati...
Stéphane Bressan, Achmad Nizar Hidayanto, C...