52 search results - page 10 / 11 » A Reinforcement Learning approach to evaluating state repres... |
CI
2005
13 years 5 months ago
2005
Autonomous agents that learn about their environment can be divided into two broad classes. One class of existing learners, reinforcement learners, typically employ weak learning ...
ML
2000
ACM
13 years 5 months ago
2000
ACM
This paper discusses a novel distributed adaptive algorithm and representation used to construct populations of adaptive Web agents. These InfoSpiders browse networked information ...
JMLR
2006
13 years 5 months ago
2006
Policy search is a method for approximately solving an optimal control problem by performing a parametric optimization search in a given class of parameterized policies. In order ...
IJCAI
2007
13 years 6 months ago
2007
A key problem in reinforcement learning is finding a good balance between the need to explore the environment and the need to gain rewards by exploiting existing knowledge. Much ...
UAI
2008
13 years 6 months ago
2008
We consider the problem of efficiently learning optimal control policies and value functions over large state spaces in an online setting in which estimates must be available afte...