Files in this item

FilesDescriptionFormat

application/pdf

application/pdfZHAO-THESIS-2019.pdf (3MB)Restricted to U of Illinois
(no description provided)PDF

Description

Title:Efficient reinforcement learning through variance reduction and trajectory synthesis
Author(s):Zhao, Xiaoming
Advisor(s):Peng, Jian
Department / Program:Computer Science
Discipline:Computer Science
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:M.S.
Genre:Thesis
Subject(s):Machine Learning, Reinforcement Learning, Optimization
Abstract:Reinforcement learning is a general and unified framework that has been proven promising for many important AI applications, such as robotics, self-driving vehicles. However, current reinforcement learning algorithms suffer from large variance and sampling inefficiency, which leads to slow convergent rate as well as unstable performance. In this thesis, we manage to alleviate these two relevant problems. For enormous variance, we combine variance reduced optimization with deep Q-learning. For inefficient sampling, we propose novel framework that integrates self-imitation learning and artificial synthesis procedure. Our approaches, which are flexible and could be extended to many tasks, prove their effectiveness through experiments on Atari and MuJoCo environment.
Issue Date:2019-04-22
Type:Text
URI:http://hdl.handle.net/2142/105067
Rights Information:Copyright 2019 Xiaoming Zhao
Date Available in IDEALS:2019-08-23
Date Deposited:2019-05


This item appears in the following Collection(s)

Item Statistics