IRUS Total

Towards Hardware Accelerated Reinforcement Learning for Application-Specific Robotic Control

File Description SizeFormat 
asap18ss.pdfAccepted version3.14 MBAdobe PDFView/Open
Title: Towards Hardware Accelerated Reinforcement Learning for Application-Specific Robotic Control
Authors: Shao, S
Tsai, J
Mysior, M
Luk, W
Chau, T
Warren, A
Jeppesen, B
Item Type: Conference Paper
Abstract: Reinforcement Learning (RL) is an area of machine learning in which an agent interacts with the environment by making sequential decisions. The agent receives reward from the environment based on how good the decisions are and tries to find an optimal decision-making policy that maximises its longterm cumulative reward. This paper presents a novel approach which has showon promise in applying accelerated simulation of RL policy training to automating the control of a real robot arm for specific applications. The approach has two steps. First, design space exploration techniques are developed to enhance performance of an FPGA accelerator for RL policy training based on Trust Region Policy Optimisation (TRPO), which results in a 43% speed improvement over a previous FPGA implementation, while achieving 4.65 times speed up against deep learning libraries running on GPU and 19.29 times speed up against CPU. Second, the trained RL policy is transferred to a real robot arm. Our experiments show that the trained arm can successfully reach to and pick up predefined objects, demonstrating the feasibility of our approach.
Issue Date: 27-Aug-2018
Date of Acceptance: 10-Jul-2018
URI: http://hdl.handle.net/10044/1/64190
DOI: https://dx.doi.org/10.1109/ASAP.2018.8445099
ISBN: 9781538674796
ISSN: 1063-6862
Publisher: IEEE
Journal / Book Title: Proceedings of the International Conference on Application-Specific Systems, Architectures and Processors
Copyright Statement: © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor/Funder: Engineering & Physical Science Research Council (E
Commission of the European Communities
Engineering & Physical Science Research Council (E
Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: PO 1977926
516075101 (EP/N031768/1)
Conference Name: 2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP)
Publication Status: Published
Start Date: 2018-07-10
Finish Date: 2018-07-12
Conference Place: Milan, Italy
Online Publication Date: 2018-08-27
Appears in Collections:Faculty of Engineering