Files in this item

FilesDescriptionFormat

application/pdf

application/pdfGE-THESIS-2018.pdf (672kB)
(no description provided)PDF

Description

Title:Solving planning problems with deep reinforcement learning and tree search
Author(s):Ge, Victor
Advisor(s):Lazebnik, Svetlana
Department / Program:Computer Science
Discipline:Computer Science
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:M.S.
Genre:Thesis
Subject(s):reinforcement learning
mcts
sokoban
a*
heuristic
Abstract:Deep reinforcement learning methods are capable of learning complex heuristics starting with no prior knowledge, but struggle in environments where the learning signal is sparse. In contrast, planning methods can discover the optimal path to a goal in the absence of external rewards, but often require a hand-crafted heuristic function to be effective. In this thesis, we describe a model-based reinforcement learning method that bridges the middle ground between these two approaches. When evaluated on the complex domain of Sokoban, the model-based method was found to be more performant, stable and sample-efficient than a model-free baseline.
Issue Date:2018-04-26
Type:Text
URI:http://hdl.handle.net/2142/101086
Rights Information:Copyright 2018 Victor Ge
Date Available in IDEALS:2018-09-04
Date Deposited:2018-05


This item appears in the following Collection(s)

Item Statistics