Graduate Thesis Or Dissertation
 

Hierarchical average reward reinforcement learning

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/f1881p57w

Descriptions

Attribute NameValues
Creator
Abstract
  • Reinforcement Learning (RL) is the study of agents that learn optimal behavior by interacting with and receiving rewards and punishments from an unknown environment. RL agents typically do this by learning value functions that assign a value to each state (situation) or to each state-action pair. Recently, there has been a growing interest in using hierarchical methods to cope with the complexity that arises due to the huge number of states found in most interesting real-world problems. Hierarchical methods seek to reduce this complexity by the use of temporal and state abstraction. Like most RL methods, most hierarchical RL methods optimize the discounted total reward that the agent receives. However, in many domains, the proper criteria to optimize is the average reward per time step. In this thesis, we adapt the concepts of hierarchical and recursive optimality, which are used to describe the kind of optimality achieved by hierarchical methods, to the average reward setting and show that they coincide under a condition called Result Distribution Invariance. We present two new model-based hierarchical RL methods, HH-learning and HAH-learning, that are intended to optimize the average reward. HH-learning is a hierarchical extension of the model-based, average-reward RL method, H-learning. Like H-learning, HH-learning requires exploration in order to learn correct domain models and optimal value function. HH-learning can be used with any exploration strategy whereas HAH-learning uses the principle of "optimism under uncertainty", which gives it a built-in "auto-exploratory" feature. We also give the hierarchical and auto-exploratory hierarchical versions of R-learning, a model-free average reward method, and a hierarchical version of ARTDP, a model-based discounted total reward method. We compare the performance of the "flat" and hierarchical methods in the task of scheduling an Automated Guided Vehicle (AGV) in a variety of settings. The results show that hierarchical methods can take advantage of temporal and state abstraction and converge in fewer steps than the flat methods. The exception is the hierarchical version of ARTDP. We give an explanation for this anomaly. Auto-exploratory hierarchical methods are faster than the hierarchical methods with ε-greedy exploration. Finally, hierarchical model-based methods are faster than hierarchical model-free methods.
License
Resource Type
Date Available
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Subject
Rights Statement
Publisher
Peer Reviewed
Language
Digitization Specifications
  • File scanned at 300 ppi (Monochrome) using ScandAll PRO 1.8.1 on a Fi-6770A in PDF format. CVista PdfCompressor 4.0 was used for pdf compression and textual OCR.
Replaces

Relationships

Parents:

This work has no parents.

In Collection:

Items