MIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • MIT Libraries
  • MIT Theses
  • Graduate Theses
  • View Item
  • DSpace@MIT Home
  • MIT Libraries
  • MIT Theses
  • Graduate Theses
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Information-theoretic Algorithms for Model-free Reinforcement Learning

Author(s)
Wu, Farrell Eldrian S.
Thumbnail
DownloadThesis PDF (423.4Kb)
Advisor
Farias, Vivek F.
Terms of use
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) Copyright retained by author(s) https://creativecommons.org/licenses/by-nc-nd/4.0/
Metadata
Show full item record
Abstract
In this work, we propose a model-free reinforcement learning algorithm for infinte-horizon, average-reward decision processes where the transition function has a finite yet unknown dependence on history, and where the induced Markov Decision Process is assumed to be weakly communicating. This algorithm combines the Lempel-Ziv (LZ) parsing tree structure for states introduced in [4] together with the optimistic Q-learning approach in [9]. We mathematically analyze the algorithm towards showing sublinear regret, providing major steps towards the proof of such. In doing so, we reduce the proof to showing sub-linearity of a key quantity related to the sum of an uncertainty metric at each step. Simulations of the algorithm will be done in a later work.
Date issued
2023-09
URI
https://hdl.handle.net/1721.1/152649
Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Publisher
Massachusetts Institute of Technology

Collections
  • Graduate Theses

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries
PrivacyPermissionsAccessibilityContact us
MIT
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.