Sciweavers

251 search results - page 44 / 51
» Skill Combination for Reinforcement Learning
Sort
View
GECCO
2006
Springer
177views Optimization» more  GECCO 2006»
15 years 9 months ago
Hyper-ellipsoidal conditions in XCS: rotation, linear approximation, and solution structure
The learning classifier system XCS is an iterative rulelearning system that evolves rule structures based on gradient-based prediction and rule quality estimates. Besides classifi...
Martin V. Butz, Pier Luca Lanzi, Stewart W. Wilson
EWCBR
2008
Springer
15 years 7 months ago
Discovering Feature Weights for Feature-based Indexing of Q-tables
In this paper we propose an approach to address the old problem of identifying the feature conditions under which a gaming strategy can be effective. For doing this, we will build ...
Chad Hogg, Stephen Lee-Urban, Bryan Auslander, H&e...
NN
2006
Springer
140views Neural Networks» more  NN 2006»
15 years 5 months ago
Neural mechanism for stochastic behaviour during a competitive game
Previous studies have shown that non-human primates can generate highly stochastic choice behaviour, especially when this is required during a competitive interaction with another...
Alireza Soltani, Daeyeol Lee, Xiao-Jing Wang
AIWORC
2000
IEEE
15 years 9 months ago
Distance Learning Using Web-Based Multimedia Environment
The "schooling industry" is faced with an inescapable demand to redefine its endeavors in terms of producing learning, rather than providing instructions. We propose a h...
Khalid J. Siddiqui, Junaid Ahmed Zubairi
INTERSPEECH
2010
15 years 2 days ago
Data-dependent evaluator modeling and its application to emotional valence classification from speech
Practical supervised learning scenarios involving subjectively evaluated data have multiple evaluators, each giving their noisy version of the hidden ground truth. Majority logic ...
Kartik Audhkhasi, Shrikanth S. Narayanan