548 search results - page 52 / 110 » A New Way to Introduce Knowledge into Reinforcement Learning |
ATAL
2004
Springer
15 years 5 months ago
2004
Springer
Product Distribution (PD) theory is a new framework for controlling Multi-Agent Systems (MAS’s). First we review one motivation of PD theory, as the information-theoretic extens...
123
click to vote
EMNLP
2011
13 years 11 months ago
2011
We propose a general method to watermark and probabilistically identify the structured outputs of machine learning algorithms. Our method is robust to local editing operations and...
AAAI
1994
15 years 1 months ago
1994
Two standard schemes for learning in classifier systems have been proposed in the literature: the bucket brigade algorithm (BBA) and the profit sharing plan (PSP). The BBA is a lo...
107
click to vote
KSEM
2010
Springer
14 years 10 months ago
2010
Springer
Given the proven usefulness of ontologies in many areas, the representation of logical axioms associated to ontological concepts and relations has become an important task in order...
CSL
2010
Springer
14 years 12 months ago
2010
Springer
We propose a unified global entropy reduction maximization (GERM) framework for active learning and semi-supervised learning for speech recognition. Active learning aims to select...