Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
Goldblatt_Thesis.pdf (1.13 MB)
ETD Abstract Container
Abstract Header
Model-Free Reinforcement Learning for Hierarchical OO-MDPs
Author Info
Goldblatt, John Dallan
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=case1642700696875092
Abstract Details
Year and Degree
2022, Master of Sciences, Case Western Reserve University, EECS - Computer and Information Sciences.
Abstract
This thesis studies Object-Oriented Markov Decision Processes (OO-MDPs), which extend MDPs with prior knowledge about the shared dynamics of similar objects in the environment. Existing work presents model-based algorithms that leverage the properties of OO-MDPs and adhere to the Knows What It Knows (KWIK) framework. In practice, models may not be easy to estimate and the KWIK framework may still lead to slow performance in a reinforcement learning context. In this thesis, I first introduce a new model-free learning algorithm for OO-MDPs based on Q-Learning. Though my approach is not KWIK, I show empirically that it exhibits significantly faster convergence than the KWIK and flat baselines. Next, I extend hierarchical reinforcement learning (HRL) to use OO-MDPs in the same manner. HRL uses a task hierarchy as prior information to reduce the overall problem into a set of smaller tasks. I show that HRL and OO-MDPs have a natural synergy, and I propose a novel model-free OO-HRL algorithm. I show empirically that this algorithm has better sample complexity than either HRL or OO-MDP algorithms alone.
Committee
Soumya Ray (Advisor)
Michael Lewicki (Committee Member)
Harold Connamacher (Committee Member)
M. Cenk Cavusoglu (Committee Member)
Pages
103 p.
Subject Headings
Artificial Intelligence
;
Computer Science
Keywords
reinforcement learning
;
RL
;
hierarchical reinforcement learning
;
HRL
;
hierarchical
;
hierarchy
;
object-oriented reinforcement learning
;
object-oriented
;
OO-MDP
;
OOMDP
;
MDP
;
Q-Learning
;
QLearning
;
MaxQ
;
KOOL
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Goldblatt, J. D. (2022).
Model-Free Reinforcement Learning for Hierarchical OO-MDPs
[Master's thesis, Case Western Reserve University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=case1642700696875092
APA Style (7th edition)
Goldblatt, John.
Model-Free Reinforcement Learning for Hierarchical OO-MDPs.
2022. Case Western Reserve University, Master's thesis.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=case1642700696875092.
MLA Style (8th edition)
Goldblatt, John. "Model-Free Reinforcement Learning for Hierarchical OO-MDPs." Master's thesis, Case Western Reserve University, 2022. http://rave.ohiolink.edu/etdc/view?acc_num=case1642700696875092
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
case1642700696875092
Download Count:
42
Copyright Info
© 2022, all rights reserved.
This open access ETD is published by Case Western Reserve University School of Graduate Studies and OhioLINK.