495 search results - page 13 / 99 » Constructing States for Reinforcement Learning |
GECCO
2003
Springer
14 years 28 days ago
2003
Springer
COLT
2008
Springer
13 years 9 months ago
2008
Springer
We propose a model-based learning algorithm, the Adaptive Aggregation Algorithm (AAA), that aims to solve the online, continuous state space reinforcement learning problem in a de...
WSC
2007
13 years 10 months ago
2007
Adaptive Time Warp protocols in the literature are usually based on a pre-defined analytic model of the system, expressed as a closed form function that maps system state to cont...
COR
2008
13 years 7 months ago
2008
Operations research and management science are often confronted with sequential decision making problems with large state spaces. Standard methods that are used for solving such c...
ICMLA
2003
13 years 9 months ago
2003
— This paper shows that the distributed representation found in Learning Vector Quantization (LVQ) enables reinforcement learning methods to cope with a large decision search spa...