Sciweavers

2440 search results - page 73 / 488
» Learn .MT: A New Approach to Incremental Learning
Sort
View
IJCNN
2006
IEEE
16 years 10 days ago
Alleviating Catastrophic Forgetting via Multi-Objective Learning
— Handling catastrophic forgetting is an interesting and challenging topic in modeling the memory mechanisms of the human brain using machine learning models. From a more general...
Yaochu Jin, Bernhard Sendhoff
NIPS
1997
15 years 7 months ago
Reinforcement Learning with Hierarchies of Machines
We present a new approach to reinforcement learning in which the policies considered by the learning process are constrained by hierarchies of partially specified machines. This ...
Ronald Parr, Stuart J. Russell
ICML
2009
IEEE
16 years 7 months ago
The adaptive k-meteorologists problem and its application to structure learning and feature selection in reinforcement learning
The purpose of this paper is three-fold. First, we formalize and study a problem of learning probabilistic concepts in the recently proposed KWIK framework. We give details of an ...
Carlos Diuk, Lihong Li, Bethany R. Leffler
GECCO
2000
Springer
114views Optimization» more  GECCO 2000»
15 years 10 months ago
Intelligent Recombination Using Individual Learning in a Collective Learning Genetic Algorithm
This paper introduces a new collective learning genetic algorithm (CLGA) which employs individual learning to do intelligent recombination based on a cooperative exchange of knowl...
Terry P. Riopka, Peter Bock
ABIALS
2008
Springer
15 years 8 months ago
Anticipatory Learning Classifier Systems and Factored Reinforcement Learning
Factored Reinforcement Learning (frl) is a new technique to solve Factored Markov Decision Problems (fmdps) when the structure of the problem is not known in advance. Like Anticipa...
Olivier Sigaud, Martin V. Butz, Olga Kozlova, Chri...