Use this URL to cite or link to this record in EThOS: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.789843
Title: Linear reinforcement learning with options
Author: Ciosek, K. A.
ISNI:       0000 0004 8502 2291
Awarding Body: UCL (University College London)
Current Institution: University College London (University of London)
Date of Award: 2015
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Abstract:
The thesis deals with linear approaches to the Markov Decision Process (MDP). In particular, we describe Policy Evaluation (PE) methods and Value Iteration (VI) methods that work with representations of MDPs that are compressed using a linear operator. We then use these methods in the context of the options framework, which is way of employing temporal abstraction to speed up MDP solving. The main novel contributions are: the analysis of convergence of the linear compression framework, a condition for when a linear compression framework is optimal, an in-depth analysis of the LSTD algorithm, the formulation of value iteration with options in the linear framework and the combination of linear state aggregation and options.
Supervisor: Silver, D. ; Shawe-Taylor, J. Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.789843  DOI: Not available
Share: