2566 search results - page 30 / 514 » Relating reinforcement learning performance to classificatio... |
PRL
2006
14 years 11 months ago
2006
Consider the class of problems in which a target class is well-defined, and an outlier class is ill-defined. In these cases new outlier classes can appear, or the class-conditiona...
100
click to vote
ICML
2006
IEEE
16 years 17 days ago
2006
IEEE
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
111
Voted
KDD
2008
ACM
16 years 5 days ago
2008
ACM
A hypergraph is a generalization of the traditional graph in which the edges are arbitrary non-empty subsets of the vertex set. It has been applied successfully to capture highord...
ICML
2006
IEEE
16 years 17 days ago
2006
IEEE
In the model-based policy search approach to reinforcement learning (RL), policies are found using a model (or "simulator") of the Markov decision process. However, for ...
ECML
2003
Springer
15 years 5 months ago
2003
Springer
Abstract. Distributed heterogeneous search environments are an emerging phenomenon in Web search, in which topic-specific search engines provide search services, and metasearchers...