End-to-End Driving in a Realistic Racing Game with Deep Reinforcement Learning

We address the problem of autonomous race car driving. Using a recent rally game (WRC6) with realistic physics and graphics we train an Asynchronous Actor Critic (A3C) in an end-to-end fashion and propose an improved reward function to learn faster. The network is trained simultaneously on three ver...

Full description

Saved in:
Bibliographic Details
Main Authors: Perot, Etienne, Jaritz, Maximilian, Toromanoff, Marin, De Charette, Raoul
Format: Conference Proceeding
Language:English
Subjects:
Automobiles
Computer architecture
Games
Learning (artificial intelligence)
Physics
Roads
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 475
container_issue
container_start_page 474
container_title
container_volume
creator Perot, Etienne
Jaritz, Maximilian
Toromanoff, Marin
De Charette, Raoul
description We address the problem of autonomous race car driving. Using a recent rally game (WRC6) with realistic physics and graphics we train an Asynchronous Actor Critic (A3C) in an end-to-end fashion and propose an improved reward function to learn faster. The network is trained simultaneously on three very different tracks (snow, mountain, and coast) with various road structures, graphics and physics. Despite the more complex environments the trained agent learns significant features and exhibits good performance while driving in a more stable way than existing end-to-end approaches.
doi_str_mv 10.1109/CVPRW.2017.64
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_8014798</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8014798</ieee_id><sourcerecordid>8014798</sourcerecordid><originalsourceid>FETCH-LOGICAL-i214t-9c4b6fe1c63bde90b0d39cd7783476b095093b7e7da38b1daa16414cab85f2893</originalsourceid><addsrcrecordid>eNotjEtLw0AURkdBsNYuXbmZP5B6b2Yyj6WktQpBJfhYlpnJjY4005IExX9vRFcHvvNxGLtAWCKCvSpfHuvXZQ6ol0oesTMshFGghVDHbJajgkwXqE7ZYhg-AADBFIUVM3a_Tk027rMJfNXHz5jeeEzc8ZrcLg5jDLx24XfduI74Vxzf-YroMPmY2n0fqKM08opcn6bXOTtp3W6gxT_n7Plm_VTeZtXD5q68rrKYoxwzG6RXLWFQwjdkwUMjbGi0NkJq5cEWYIXXpBsnjMfGOVQSZXDeFG1urJizy79uJKLtoY-d67-3BlBqa8QPHL1M7A</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>End-to-End Driving in a Realistic Racing Game with Deep Reinforcement Learning</title><source>IEEE Xplore All Conference Series</source><creator>Perot, Etienne ; Jaritz, Maximilian ; Toromanoff, Marin ; De Charette, Raoul</creator><creatorcontrib>Perot, Etienne ; Jaritz, Maximilian ; Toromanoff, Marin ; De Charette, Raoul</creatorcontrib><description>We address the problem of autonomous race car driving. Using a recent rally game (WRC6) with realistic physics and graphics we train an Asynchronous Actor Critic (A3C) in an end-to-end fashion and propose an improved reward function to learn faster. The network is trained simultaneously on three very different tracks (snow, mountain, and coast) with various road structures, graphics and physics. Despite the more complex environments the trained agent learns significant features and exhibits good performance while driving in a more stable way than existing end-to-end approaches.</description><identifier>EISSN: 2160-7516</identifier><identifier>EISBN: 1538607336</identifier><identifier>EISBN: 9781538607336</identifier><identifier>DOI: 10.1109/CVPRW.2017.64</identifier><identifier>CODEN: IEEPAD</identifier><language>eng</language><publisher>IEEE</publisher><subject>Automobiles ; Computer architecture ; Games ; Learning (artificial intelligence) ; Physics ; Roads ; Training</subject><ispartof>2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017, p.474-475</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8014798$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,23930,23931,25140,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8014798$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Perot, Etienne</creatorcontrib><creatorcontrib>Jaritz, Maximilian</creatorcontrib><creatorcontrib>Toromanoff, Marin</creatorcontrib><creatorcontrib>De Charette, Raoul</creatorcontrib><title>End-to-End Driving in a Realistic Racing Game with Deep Reinforcement Learning</title><title>2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</title><addtitle>CVPRW</addtitle><description>We address the problem of autonomous race car driving. Using a recent rally game (WRC6) with realistic physics and graphics we train an Asynchronous Actor Critic (A3C) in an end-to-end fashion and propose an improved reward function to learn faster. The network is trained simultaneously on three very different tracks (snow, mountain, and coast) with various road structures, graphics and physics. Despite the more complex environments the trained agent learns significant features and exhibits good performance while driving in a more stable way than existing end-to-end approaches.</description><subject>Automobiles</subject><subject>Computer architecture</subject><subject>Games</subject><subject>Learning (artificial intelligence)</subject><subject>Physics</subject><subject>Roads</subject><subject>Training</subject><issn>2160-7516</issn><isbn>1538607336</isbn><isbn>9781538607336</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2017</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjEtLw0AURkdBsNYuXbmZP5B6b2Yyj6WktQpBJfhYlpnJjY4005IExX9vRFcHvvNxGLtAWCKCvSpfHuvXZQ6ol0oesTMshFGghVDHbJajgkwXqE7ZYhg-AADBFIUVM3a_Tk027rMJfNXHz5jeeEzc8ZrcLg5jDLx24XfduI74Vxzf-YroMPmY2n0fqKM08opcn6bXOTtp3W6gxT_n7Plm_VTeZtXD5q68rrKYoxwzG6RXLWFQwjdkwUMjbGi0NkJq5cEWYIXXpBsnjMfGOVQSZXDeFG1urJizy79uJKLtoY-d67-3BlBqa8QPHL1M7A</recordid><startdate>201707</startdate><enddate>201707</enddate><creator>Perot, Etienne</creator><creator>Jaritz, Maximilian</creator><creator>Toromanoff, Marin</creator><creator>De Charette, Raoul</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201707</creationdate><title>End-to-End Driving in a Realistic Racing Game with Deep Reinforcement Learning</title><author>Perot, Etienne ; Jaritz, Maximilian ; Toromanoff, Marin ; De Charette, Raoul</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i214t-9c4b6fe1c63bde90b0d39cd7783476b095093b7e7da38b1daa16414cab85f2893</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Automobiles</topic><topic>Computer architecture</topic><topic>Games</topic><topic>Learning (artificial intelligence)</topic><topic>Physics</topic><topic>Roads</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Perot, Etienne</creatorcontrib><creatorcontrib>Jaritz, Maximilian</creatorcontrib><creatorcontrib>Toromanoff, Marin</creatorcontrib><creatorcontrib>De Charette, Raoul</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Perot, Etienne</au><au>Jaritz, Maximilian</au><au>Toromanoff, Marin</au><au>De Charette, Raoul</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>End-to-End Driving in a Realistic Racing Game with Deep Reinforcement Learning</atitle><btitle>2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</btitle><stitle>CVPRW</stitle><date>2017-07</date><risdate>2017</risdate><spage>474</spage><epage>475</epage><pages>474-475</pages><eissn>2160-7516</eissn><eisbn>1538607336</eisbn><eisbn>9781538607336</eisbn><coden>IEEPAD</coden><abstract>We address the problem of autonomous race car driving. Using a recent rally game (WRC6) with realistic physics and graphics we train an Asynchronous Actor Critic (A3C) in an end-to-end fashion and propose an improved reward function to learn faster. The network is trained simultaneously on three very different tracks (snow, mountain, and coast) with various road structures, graphics and physics. Despite the more complex environments the trained agent learns significant features and exhibits good performance while driving in a more stable way than existing end-to-end approaches.</abstract><pub>IEEE</pub><doi>10.1109/CVPRW.2017.64</doi><tpages>2</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2160-7516
ispartof 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017, p.474-475
issn 2160-7516
language eng
recordid cdi_ieee_primary_8014798
source IEEE Xplore All Conference Series
subjects Automobiles
Computer architecture
Games
Learning (artificial intelligence)
Physics
Roads
Training
title End-to-End Driving in a Realistic Racing Game with Deep Reinforcement Learning
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T18%3A25%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=End-to-End%20Driving%20in%20a%20Realistic%20Racing%20Game%20with%20Deep%20Reinforcement%20Learning&rft.btitle=2017%20IEEE%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20(CVPRW)&rft.au=Perot,%20Etienne&rft.date=2017-07&rft.spage=474&rft.epage=475&rft.pages=474-475&rft.eissn=2160-7516&rft.coden=IEEPAD&rft_id=info:doi/10.1109/CVPRW.2017.64&rft.eisbn=1538607336&rft.eisbn_list=9781538607336&rft_dat=%3Cieee_CHZPO%3E8014798%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i214t-9c4b6fe1c63bde90b0d39cd7783476b095093b7e7da38b1daa16414cab85f2893%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=8014798&rfr_iscdi=true