Please use this identifier to cite or link to this item: http://ktisis.cut.ac.cy/handle/10488/8205
Title: A non-stationary infinite partially-observable markov decision process
Authors: Kosmopoulos, Dimitrios 
Chatzis, Sotirios P. 
Keywords: Markov decision processes
Bayesian methods
Issue Date: 2014
Source: 24th International Conference on Artificial Neural Networks, 2014, Hamburg, Germany, 15–19 September
Abstract: Partially Observable Markov Decision Processes (POMDPs) have been met with great success in planning domains where agents must balance actions that provide knowledge and actions that provide reward. Recently, nonparametric Bayesian methods have been success- fully applied to POMDPs to obviate the need of a priori knowledge of the size of the state space, allowing to assume that the number of visited states may grow as the agent explores its environment. These approaches rely on the assumption that the agent's environment remains stationary; however, in real-world scenarios the environment may change over time. In this work, we aim to address this inadequacy by introducing a dynamic nonparametric Bayesian POMDP model that both allows for automatic inference of the (distributional) representations of POMDP states, and for capturing non-stationarity in the modeled environments. Formulation of our method is based on imposition of a suitable dynamic hierarchical Dirichlet process (dHDP) prior over state transitions. We derive e cientalgorithms for model inference and action planning and evaluate it on several benchmark tasks.
URI: http://ktisis.cut.ac.cy/jspui/handle/10488/8205
Appears in Collections:Δημοσιεύσεις σε συνέδρια/Conference papers

Files in This Item:
File Description SizeFormat 
Chatzis.pdf196.62 kBAdobe PDFView/Open
Show full item record

Page view(s) 20

22
Last Week
2
Last month
checked on May 26, 2017

Download(s) 5

18
checked on May 26, 2017

Google ScholarTM

Check


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