Sciweavers

246 search results - page 13 / 50
» Learning a Fine Vocabulary
Sort
View
ICML
2010
IEEE
15 years 3 days ago
Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis
We introduce new, efficient algorithms for value iteration with multiple reward functions and continuous state. We also give an algorithm for finding the set of all nondominated a...
Daniel J. Lizotte, Michael H. Bowling, Susan A. Mu...
COLT
2008
Springer
15 years 25 days ago
Adaptive Aggregation for Reinforcement Learning with Efficient Exploration: Deterministic Domains
We propose a model-based learning algorithm, the Adaptive Aggregation Algorithm (AAA), that aims to solve the online, continuous state space reinforcement learning problem in a de...
Andrey Bernstein, Nahum Shimkin
MC
2008
137views Computer Science» more  MC 2008»
15 years 14 days ago
Between 'Instructions' and 'Diy': Tagging in Learning Communities
In this paper, we discuss the novel technology tagging and the results of analyzing a learning community in a popular system that relies on tagging namely YouTube. We present our ...
Milena Reichel, Heidi Schelhowe
COLT
2006
Springer
15 years 2 months ago
Active Sampling for Multiple Output Identification
We study functions with multiple output values, and use active sampling to identify an example for each of the possible output values. Our results for this setting include: (1) Eff...
Shai Fine, Yishay Mansour
ANLP
1997
103views more  ANLP 1997»
15 years 12 days ago
The NLP Role in Animated Conversation for CALL
Language learning is a relatively new application for natural language processing (NLP) and for intelligent tutoring and learning environments (ITLEs). NLP has a crucial role to p...
Michael Schoelles, Henry Hamburger