Sciweavers

1829 search results - page 167 / 366
» On Learning Soccer Strategies
Sort
View
ISDA
2009
IEEE
16 years 1 months ago
Postponed Updates for Temporal-Difference Reinforcement Learning
This paper presents postponed updates, a new strategy for TD methods that can improve sample efficiency without incurring the computational and space requirements of model-based ...
Harm van Seijen, Shimon Whiteson
CP
2004
Springer
15 years 11 months ago
Decomposition and Learning for a Hard Real Time Task Allocation Problem
Abstract. We present a cooperation technique using an accurate management of nogoods to solve a hard real-time problem which consists in assigning periodic tasks to processors in t...
Hadrien Cambazard, Pierre-Emmanuel Hladik, Anne-Ma...
EDM
2010
101views Data Mining» more  EDM 2010»
15 years 7 months ago
Off Topic Conversation in Expert Tutoring: Waste of Time or Learning Opportunity
While many aspects of tutoring have been identified and studied, off topic conversation has been largely ignored. In this paper, off topic conversation during 50 hours of one-to-on...
Blair Lehman, Whitney L. Cade, Andrew Olney
CSREAEEE
2008
128views Business» more  CSREAEEE 2008»
15 years 7 months ago
Public relations System for Mobile Learning
- In this paper, we proposed an automatic pushing system, whereby the users of mobile devices set their preferences on the Internet and receive `pushed' contents, which are a ...
Chul-Woo Kim, Misook Lim, Young-Min Chin
GIS
2008
ACM
15 years 6 months ago
An ACS cooperative learning approach for route finding in natural environment
This paper introduces an ant-based colony system for the representation of a verbal route description. It is grounded on a natural metaphor that mimics the behavior of ant colonie...
David Brosset, Christophe Claramunt, Eric Saux