Loading…
Imitation learning of car driving skills with decision trees and random forests
Machine learning is an appealing and useful approach to creating vehicle control algorithms, both for simulated and real vehicles. One common learning scenario that is often possible to apply is learning by imitation, in which the behavior of an exemplary driver provides training instances for a sup...
Saved in:
Published in: | International journal of applied mathematics and computer science 2014-09, Vol.24 (3), p.579-597 |
---|---|
Main Authors: | , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c459t-c62499b31007b8b3194ea777fdb25034a5d696216315e66df93ca417241ad9b33 |
---|---|
cites | |
container_end_page | 597 |
container_issue | 3 |
container_start_page | 579 |
container_title | International journal of applied mathematics and computer science |
container_volume | 24 |
creator | Cichosz, Paweł Pawełczak, Łukasz |
description | Machine learning is an appealing and useful approach to creating vehicle control algorithms, both for simulated and real vehicles. One common learning scenario that is often possible to apply is learning by imitation, in which the behavior of an exemplary driver provides training instances for a supervised learning algorithm. This article follows this approach in the domain of simulated car racing, using the TORCS simulator. In contrast to most prior work on imitation learning, a symbolic decision tree knowledge representation is adopted, which combines potentially high accuracy with human readability, an advantage that can be important in many applications. Decision trees are demonstrated to be capable of representing high quality control models, reaching the performance level of sophisticated pre-designed algorithms. This is achieved by enhancing the basic imitation learning scenario to include active retraining, automatically triggered on control failures. It is also demonstrated how better stability and generalization can be achieved by sacrificing human-readability and using decision tree model ensembles. The methodology for learning control models contributed by this article can be hopefully applied to solve real-world control tasks, as well as to develop video game bots |
doi_str_mv | 10.2478/amcs-2014-0042 |
format | article |
fullrecord | <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_e75ad78985534beeaa4db6876e0bec7e</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_e75ad78985534beeaa4db6876e0bec7e</doaj_id><sourcerecordid>1642239446</sourcerecordid><originalsourceid>FETCH-LOGICAL-c459t-c62499b31007b8b3194ea777fdb25034a5d696216315e66df93ca417241ad9b33</originalsourceid><addsrcrecordid>eNptkc1r3DAQxU1JoUnaa8-CXnJxom9Z0EsITbIQyCU9i7E03mprW6nkbch_X7lbSgi5zIyG33toeE3zmdFzLk13AZMvLadMtpRK_q455rQTbSctP3oxf2hOStlRyi014ri530xxgSWmmYwIeY7zlqSBeMgk5Ph7fZafcRwLeYrLDxLQx7LCS0YsBOZAci1pIkPKWJbysXk_wFjw079-2ny__vZwddve3d9sri7vWi-VXVqvubS2F4xS03e1W4lgjBlCzxUVElTQVnOmBVOodRis8CCZ4ZJBqDpx2mwOviHBzj3mOEF-dgmi-7tIeesgL9GP6NAoCKaznVJC9ogAMvS6Mxppj95g9To7eD3m9Gtfr3BTLB7HEWZM--KYlpwLK6Wu6JdX6C7t81wvrRRXnFulaaXOD5TPqZSMw_8PMurWrNyalVuzcmtWVfD1IHiCccEccJv3z3V44f6mkEuhjBV_AKRwmkc</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1625229560</pqid></control><display><type>article</type><title>Imitation learning of car driving skills with decision trees and random forests</title><source>Freely Accessible Science Journals</source><source>Publicly Available Content (ProQuest)</source><creator>Cichosz, Paweł ; Pawełczak, Łukasz</creator><creatorcontrib>Cichosz, Paweł ; Pawełczak, Łukasz</creatorcontrib><description>Machine learning is an appealing and useful approach to creating vehicle control algorithms, both for simulated and real vehicles. One common learning scenario that is often possible to apply is learning by imitation, in which the behavior of an exemplary driver provides training instances for a supervised learning algorithm. This article follows this approach in the domain of simulated car racing, using the TORCS simulator. In contrast to most prior work on imitation learning, a symbolic decision tree knowledge representation is adopted, which combines potentially high accuracy with human readability, an advantage that can be important in many applications. Decision trees are demonstrated to be capable of representing high quality control models, reaching the performance level of sophisticated pre-designed algorithms. This is achieved by enhancing the basic imitation learning scenario to include active retraining, automatically triggered on control failures. It is also demonstrated how better stability and generalization can be achieved by sacrificing human-readability and using decision tree model ensembles. The methodology for learning control models contributed by this article can be hopefully applied to solve real-world control tasks, as well as to develop video game bots</description><identifier>ISSN: 2083-8492</identifier><identifier>ISSN: 1641-876X</identifier><identifier>EISSN: 2083-8492</identifier><identifier>DOI: 10.2478/amcs-2014-0042</identifier><language>eng</language><publisher>Zielona Góra: De Gruyter Open</publisher><subject>Algorithms ; Automobiles ; Automotive engineering ; autonomous driving ; behavioral cloning ; car racing ; Computer simulation ; control ; Decision trees ; imitation learning ; Learning ; Mathematical models ; model ensembles ; random forest ; Retraining</subject><ispartof>International journal of applied mathematics and computer science, 2014-09, Vol.24 (3), p.579-597</ispartof><rights>Copyright De Gruyter Open Sp. z o.o. Sep 2014</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c459t-c62499b31007b8b3194ea777fdb25034a5d696216315e66df93ca417241ad9b33</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/1625229560?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,25753,27924,27925,37012,37013,44590</link.rule.ids></links><search><creatorcontrib>Cichosz, Paweł</creatorcontrib><creatorcontrib>Pawełczak, Łukasz</creatorcontrib><title>Imitation learning of car driving skills with decision trees and random forests</title><title>International journal of applied mathematics and computer science</title><description>Machine learning is an appealing and useful approach to creating vehicle control algorithms, both for simulated and real vehicles. One common learning scenario that is often possible to apply is learning by imitation, in which the behavior of an exemplary driver provides training instances for a supervised learning algorithm. This article follows this approach in the domain of simulated car racing, using the TORCS simulator. In contrast to most prior work on imitation learning, a symbolic decision tree knowledge representation is adopted, which combines potentially high accuracy with human readability, an advantage that can be important in many applications. Decision trees are demonstrated to be capable of representing high quality control models, reaching the performance level of sophisticated pre-designed algorithms. This is achieved by enhancing the basic imitation learning scenario to include active retraining, automatically triggered on control failures. It is also demonstrated how better stability and generalization can be achieved by sacrificing human-readability and using decision tree model ensembles. The methodology for learning control models contributed by this article can be hopefully applied to solve real-world control tasks, as well as to develop video game bots</description><subject>Algorithms</subject><subject>Automobiles</subject><subject>Automotive engineering</subject><subject>autonomous driving</subject><subject>behavioral cloning</subject><subject>car racing</subject><subject>Computer simulation</subject><subject>control</subject><subject>Decision trees</subject><subject>imitation learning</subject><subject>Learning</subject><subject>Mathematical models</subject><subject>model ensembles</subject><subject>random forest</subject><subject>Retraining</subject><issn>2083-8492</issn><issn>1641-876X</issn><issn>2083-8492</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><sourceid>DOA</sourceid><recordid>eNptkc1r3DAQxU1JoUnaa8-CXnJxom9Z0EsITbIQyCU9i7E03mprW6nkbch_X7lbSgi5zIyG33toeE3zmdFzLk13AZMvLadMtpRK_q455rQTbSctP3oxf2hOStlRyi014ri530xxgSWmmYwIeY7zlqSBeMgk5Ph7fZafcRwLeYrLDxLQx7LCS0YsBOZAci1pIkPKWJbysXk_wFjw079-2ny__vZwddve3d9sri7vWi-VXVqvubS2F4xS03e1W4lgjBlCzxUVElTQVnOmBVOodRis8CCZ4ZJBqDpx2mwOviHBzj3mOEF-dgmi-7tIeesgL9GP6NAoCKaznVJC9ogAMvS6Mxppj95g9To7eD3m9Gtfr3BTLB7HEWZM--KYlpwLK6Wu6JdX6C7t81wvrRRXnFulaaXOD5TPqZSMw_8PMurWrNyalVuzcmtWVfD1IHiCccEccJv3z3V44f6mkEuhjBV_AKRwmkc</recordid><startdate>20140901</startdate><enddate>20140901</enddate><creator>Cichosz, Paweł</creator><creator>Pawełczak, Łukasz</creator><general>De Gruyter Open</general><general>De Gruyter Poland</general><general>Sciendo</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7SC</scope><scope>7XB</scope><scope>8AL</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BYOGL</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>L6V</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>M0N</scope><scope>M7S</scope><scope>P5Z</scope><scope>P62</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PTHSS</scope><scope>Q9U</scope><scope>S0W</scope><scope>DOA</scope></search><sort><creationdate>20140901</creationdate><title>Imitation learning of car driving skills with decision trees and random forests</title><author>Cichosz, Paweł ; Pawełczak, Łukasz</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c459t-c62499b31007b8b3194ea777fdb25034a5d696216315e66df93ca417241ad9b33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Algorithms</topic><topic>Automobiles</topic><topic>Automotive engineering</topic><topic>autonomous driving</topic><topic>behavioral cloning</topic><topic>car racing</topic><topic>Computer simulation</topic><topic>control</topic><topic>Decision trees</topic><topic>imitation learning</topic><topic>Learning</topic><topic>Mathematical models</topic><topic>model ensembles</topic><topic>random forest</topic><topic>Retraining</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Cichosz, Paweł</creatorcontrib><creatorcontrib>Pawełczak, Łukasz</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Computer and Information Systems Abstracts</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Computing Database (Alumni Edition)</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>East Europe, Central Europe Database</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer science database</collection><collection>ProQuest Engineering Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Computing Database</collection><collection>Engineering Database</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>Publicly Available Content (ProQuest)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Engineering Collection</collection><collection>ProQuest Central Basic</collection><collection>DELNET Engineering & Technology Collection</collection><collection>Directory of Open Access Journals</collection><jtitle>International journal of applied mathematics and computer science</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Cichosz, Paweł</au><au>Pawełczak, Łukasz</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Imitation learning of car driving skills with decision trees and random forests</atitle><jtitle>International journal of applied mathematics and computer science</jtitle><date>2014-09-01</date><risdate>2014</risdate><volume>24</volume><issue>3</issue><spage>579</spage><epage>597</epage><pages>579-597</pages><issn>2083-8492</issn><issn>1641-876X</issn><eissn>2083-8492</eissn><abstract>Machine learning is an appealing and useful approach to creating vehicle control algorithms, both for simulated and real vehicles. One common learning scenario that is often possible to apply is learning by imitation, in which the behavior of an exemplary driver provides training instances for a supervised learning algorithm. This article follows this approach in the domain of simulated car racing, using the TORCS simulator. In contrast to most prior work on imitation learning, a symbolic decision tree knowledge representation is adopted, which combines potentially high accuracy with human readability, an advantage that can be important in many applications. Decision trees are demonstrated to be capable of representing high quality control models, reaching the performance level of sophisticated pre-designed algorithms. This is achieved by enhancing the basic imitation learning scenario to include active retraining, automatically triggered on control failures. It is also demonstrated how better stability and generalization can be achieved by sacrificing human-readability and using decision tree model ensembles. The methodology for learning control models contributed by this article can be hopefully applied to solve real-world control tasks, as well as to develop video game bots</abstract><cop>Zielona Góra</cop><pub>De Gruyter Open</pub><doi>10.2478/amcs-2014-0042</doi><tpages>19</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2083-8492 |
ispartof | International journal of applied mathematics and computer science, 2014-09, Vol.24 (3), p.579-597 |
issn | 2083-8492 1641-876X 2083-8492 |
language | eng |
recordid | cdi_doaj_primary_oai_doaj_org_article_e75ad78985534beeaa4db6876e0bec7e |
source | Freely Accessible Science Journals; Publicly Available Content (ProQuest) |
subjects | Algorithms Automobiles Automotive engineering autonomous driving behavioral cloning car racing Computer simulation control Decision trees imitation learning Learning Mathematical models model ensembles random forest Retraining |
title | Imitation learning of car driving skills with decision trees and random forests |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T14%3A02%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Imitation%20learning%20of%20car%20driving%20skills%20with%20decision%20trees%20and%20random%20forests&rft.jtitle=International%20journal%20of%20applied%20mathematics%20and%20computer%20science&rft.au=Cichosz,%20Pawe%C5%82&rft.date=2014-09-01&rft.volume=24&rft.issue=3&rft.spage=579&rft.epage=597&rft.pages=579-597&rft.issn=2083-8492&rft.eissn=2083-8492&rft_id=info:doi/10.2478/amcs-2014-0042&rft_dat=%3Cproquest_doaj_%3E1642239446%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c459t-c62499b31007b8b3194ea777fdb25034a5d696216315e66df93ca417241ad9b33%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1625229560&rft_id=info:pmid/&rfr_iscdi=true |