Sciweavers

1800 search results - page 57 / 360
» Learning Restart Strategies
Sort
View
ICML
2003
IEEE
14 years 10 months ago
AWESOME: A General Multiagent Learning Algorithm that Converges in Self-Play and Learns a Best Response Against Stationary Oppon
A satisfactory multiagent learning algorithm should, at a minimum, learn to play optimally against stationary opponents and converge to a Nash equilibrium in self-play. The algori...
Vincent Conitzer, Tuomas Sandholm
ITS
2010
Springer
157views Multimedia» more  ITS 2010»
14 years 2 months ago
A Computational Model of Accelerated Future Learning through Feature Recognition
Accelerated future learning, in which learning proceeds more effectively and more rapidly because of prior learning, is considered to be one of the most interesting measures of ro...
Nan Li, William W. Cohen, Kenneth R. Koedinger
KDD
1995
ACM
148views Data Mining» more  KDD 1995»
14 years 1 months ago
Learning Arbiter and Combiner Trees from Partitioned Data for Scaling Machine Learning
Knowledge discovery in databases has become an increasingly important research topic with the advent of wide area network computing. One of the crucial problems we study in this p...
Philip K. Chan, Salvatore J. Stolfo
SGAI
2009
Springer
14 years 4 months ago
Explaining How to Play Real-Time Strategy Games
Real-time strategy games share many aspects with real situations in domains such as battle planning, air traffic control, and emergency response team management which makes them a...
Ronald A. Metoyer, Simone Stumpf, Christoph Neuman...
AIED
2009
Springer
14 years 4 months ago
Discovering Tutorial Dialogue Strategies with Hidden Markov Models
Identifying effective tutorial strategies is a key problem for tutorial dialogue systems research. Ongoing work in human-human tutorial dialogue continues to reveal the complex phe...
Kristy Elizabeth Boyer, Eunyoung Ha, Michael D. Wa...