Show simple item record

dc.contributor.authorJhunjhunwala, Aman 20:09:22 (GMT) 05:50:08 (GMT)
dc.description.abstractRecently, deep neural networks have been capable of solving complex control tasks in certain challenging environments. However, these deep learning policies continue to be hard to interpret, explain and verify which limits their practical applicability. Decision Trees lend themselves well to explanation and verification tools but are not easy to train especially in an online fashion. The aim of this thesis is to explore online tree construction algorithms and demonstrate the technique and effectiveness of distilling reinforcement learning policies into a Bayesian tree structure. We introduce Q-BSP Trees and an Ordered Sequential Monte Carlo training algorithm that helps condense the Q-function from fully trained Deep Q-Networks into the tree structure. QBSP Forests generate partitioning rules that transparently reconstruct the value function for all possible states. It convincingly beats performance benchmarks provided by earlier policy distillation methods resulting in performance closest to the original Deep Learning policy.en
dc.publisherUniversity of Waterlooen
dc.subject.lcshNeural networks (Computer science)en
dc.subject.lcshMachine learningen
dc.titlePolicy Extraction via Online Q-Value Distillationen
dc.typeMaster Thesisen
dc.pendingfalse R. Cheriton School of Computer Scienceen Scienceen of Waterlooen
uws-etd.degreeMaster of Mathematicsen
uws-etd.embargo.terms4 monthsen
uws.contributor.advisorCzarnecki, Krzysztof
uws.contributor.affiliation1Faculty of Mathematicsen

Files in this item


This item appears in the following Collection(s)

Show simple item record


University of Waterloo Library
200 University Avenue West
Waterloo, Ontario, Canada N2L 3G1
519 888 4883

All items in UWSpace are protected by copyright, with all rights reserved.

DSpace software

Service outages