2566 search results - page 156 / 514 » Relating reinforcement learning performance to classificatio... |
139
click to vote
ICCBR
2010
Springer
15 years 8 months ago
2010
Springer
In this paper we present an approach for reducing the memory footprint requirement of temporal difference methods in which the set of states is finite. We use case-based generaliza...
138
click to vote
NIPS
1993
15 years 5 months ago
1993
The game of Go has a high branching factor that defeats the tree search approach used in computer chess, and long-range spatiotemporal interactions that make position evaluation e...
130
click to vote
AR
2002
15 years 4 months ago
2002
Abstract--A prominent emerging theory of sensorimotor development in biological systems proposes that control knowledge is encoded in the dynamics of physical interaction with the ...
131
click to vote
ICML
1994
IEEE
15 years 8 months ago
1994
IEEE
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
151
click to vote
ECLIPSE
2007
ACM
15 years 8 months ago
2007
ACM
We present a tool that predicts whether the software under development inside an IDE has a bug. An IDE plugin performs this prediction, using the Change Classification technique t...