4930 search results - page 14 / 986 » Learning minimal abstractions |
ICML
2004
IEEE
16 years 1 months ago
2004
IEEE
Abstraction in Reinforcement Learning via Clustering Shie Mannor shie@mit.edu Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA ...
103
Voted
ISNN
2005
Springer
15 years 5 months ago
2005
Springer
Abstract. This paper proposes a novel algorithm based on informax for postnonlinear blind source separation. The demixing system culminates to a neural network with sandwiched stru...
NIPS
2004
15 years 1 months ago
2004
We consider the semi-supervised learning problem, where a decision rule is to be learned from labeled and unlabeled data. In this framework, we motivate minimum entropy regulariza...
101
click to vote
ICML
2004
IEEE
16 years 1 months ago
2004
IEEE
lative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning ?Ozg?ur S?im?sek ozgur@cs.umass.edu Andrew G. Barto barto@cs.umass.edu Department of Computer Scie...
123
Voted
COLT
2010
Springer
14 years 10 months ago
2010
Springer
In standard online learning, the goal of the learner is to maintain an average loss that is "not too big" compared to the loss of the best-performing function in a fixed...