Back to Search
Start Over
Bottom-up learning of hierarchical models in a class of deterministic POMDP environments
- Source :
- International Journal of Applied Mathematics and Computer Science, Vol 25, Iss 3, Pp 597-615 (2015)
- Publication Year :
- 2015
- Publisher :
- Walter de Gruyter GmbH, 2015.
-
Abstract
- The theory of partially observable Markov decision processes (POMDPs) is a useful tool for developing various intelligent agents, and learning hierarchical POMDP models is one of the key approaches for building such agents when the environments of the agents are unknown and large. To learn hierarchical models, bottom-up learning methods in which learning takes place in a layer-by-layer manner from the lowest to the highest layer are already extensively used in some research fields such as hidden Markov models and neural networks. However, little attention has been paid to bottom-up approaches for learning POMDP models. In this paper, we present a novel bottom-up learning algorithm for hierarchical POMDP models and prove that, by using this algorithm, a perfect model (i.e., a model that can perfectly predict future observations) can be learned at least in a class of deterministic POMDP environments
- Subjects :
- partially observable markov decision processes
Computer science
computer.software_genre
Markov model
Machine learning
ComputingMethodologies_ARTIFICIALINTELLIGENCE
Hierarchical database model
Intelligent agent
QA1-939
Computer Science (miscellaneous)
Hidden Markov model
bottom-up learning
Engineering (miscellaneous)
hierarchical models
Class (computer programming)
Artificial neural network
business.industry
Applied Mathematics
Partially observable Markov decision process
QA75.5-76.95
Electronic computers. Computer science
Markov decision process
Artificial intelligence
business
computer
Mathematics
Subjects
Details
- ISSN :
- 20838492
- Volume :
- 25
- Database :
- OpenAIRE
- Journal :
- International Journal of Applied Mathematics and Computer Science
- Accession number :
- edsair.doi.dedup.....6c958f331b73d374a45012f86fc7a7a7