9841 search results - page 794 / 1969 » Distributed Value Functions |
219
click to vote
ICMLA
2010
15 years 5 months ago
2010
Abstract-- Policy Gradients with Parameter-based Exploration (PGPE) is a novel model-free reinforcement learning method that alleviates the problem of high-variance gradient estima...
218
click to vote
CONCUR
2009
Springer
15 years 5 months ago
2009
Springer
Convergence is often the key liveness property for distributed systems that interact with physical processes. Techniques for proving convergence (asymptotic stability) have been ex...
212
click to vote
JMLR
2010
15 years 2 months ago
2010
While most popular collaborative filtering methods use low-rank matrix factorization and parametric density assumptions, this article proposes an approach based on distribution-fr...
234
click to vote
IJCNN
2007
IEEE
16 years 2 months ago
2007
IEEE
—Default ARTMAP combines winner-take-all category node activation during training, distributed activation during testing, and a set of default parameter values that define a read...
194
click to vote
DEXAW
2005
IEEE
16 years 1 months ago
2005
IEEE
Ontologies provide a means of modelling and representing a knowledge domain. Such representation, already used in purpose-built distributed information systems, can also be of gre...