Please use this identifier to cite or link to this item: https://ktisis.cut.ac.cy/handle/10488/8206
Title: A partially-observable markov decision process for dealing with dynamically changing environments
Authors: Chatzis, Sotirios P. 
Kosmopoulos, Dimitrios I. 
Keywords: POMDP problem;Bayesian non-parametrics;Dirichlet process
Category: Computer and Information Sciences
Field: Engineering and Technology
Issue Date: 2014
Source: 10th International Conference on Artificial Intelligence Applications and Innovations, 2014, Rhodes, Greece, 19-21 September, pp. 111-120
Conference: IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations 
Abstract: This paper offers a solution to the non-stationary POMDP problem, by making use of methods and concepts from the field of Bayesian non-parametrics, specifically dynamic hierarchical Dirichlet process priors. We combine block Gibbs sampling and importance sampling to perform inference. We evaluate the method in several benchmark policy learning tasks
Description: Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, vol. 436).
URI: http://ktisis.cut.ac.cy/handle/10488/8206
ISBN: 978-3-662-44654-6 (online)
978-3-662-44653-9 (print)
DOI: 10.1007/978-3-662-44654-6_11
Type: Conference Papers
Appears in Collections:Δημοσιεύσεις σε συνέδρια/Conference papers

Show full item record

Page view(s)

89
Last Week
1
Last month
3
checked on Aug 18, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.