{"id":"https://openalex.org/W3126775045","doi":"https://doi.org/10.5220/0010256208740881","title":"Explainable Reinforcement Learning for Longitudinal Control","display_name":"Explainable Reinforcement Learning for Longitudinal Control","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3126775045","doi":"https://doi.org/10.5220/0010256208740881","mag":"3126775045"},"language":"en","primary_location":{"id":"doi:10.5220/0010256208740881","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0010256208740881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008213233","display_name":"Roman Lie\u00dfner","orcid":"https://orcid.org/0009-0004-2014-6899"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Roman Liessner","raw_affiliation_strings":["Dresden Institute of Automobile Engineering, TU Dresden, George-B\u00e4hr-Stra\u00dfe 1, Dresden, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dresden Institute of Automobile Engineering, TU Dresden, George-B\u00e4hr-Stra\u00dfe 1, Dresden, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086568055","display_name":"Jan Dohmen","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Dohmen","raw_affiliation_strings":["Dresden Institute of Automobile Engineering, TU Dresden, George-B\u00e4hr-Stra\u00dfe 1, Dresden, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dresden Institute of Automobile Engineering, TU Dresden, George-B\u00e4hr-Stra\u00dfe 1, Dresden, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060596453","display_name":"Marco Wiering","orcid":"https://orcid.org/0000-0003-4331-7537"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marco Wiering","raw_affiliation_strings":["Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, 9747 AG Groningen, The Netherlands, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, 9747 AG Groningen, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4317,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88188862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"874","last_page":"881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.5954999923706055,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.5954999923706055,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.5533999800682068,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5115000009536743,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.822818398475647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6867306232452393},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5035781264305115},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.48684924840927124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4064514636993408},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32609182596206665},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13224443793296814}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.822818398475647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6867306232452393},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5035781264305115},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48684924840927124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4064514636993408},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32609182596206665},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13224443793296814},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5220/0010256208740881","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0010256208740881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/d455a9ae-5dcc-4d7d-9967-84959e532fb5","is_oa":false,"landing_page_url":"https://research.rug.nl/en/publications/d455a9ae-5dcc-4d7d-9967-84959e532fb5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Liessner, R, Dohmen, J & Wiering, M 2021, Explainable Reinforcement Learning for Longitudinal Control. in A P Rocha, L Steels & J van den Herik (eds), Proceedings of the 13th International Conference on Agents and Artificial Intelligence. ICAART 2021 , vol. 2, SciTePress, pp. 874-881, 13th International Conference on Agents and Artificial Intelligence, ICAART 2021, Virtual, Online, 04/02/2021.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.rug.nl:publications/d455a9ae-5dcc-4d7d-9967-84959e532fb5","is_oa":false,"landing_page_url":"https://hdl.handle.net/11370/d455a9ae-5dcc-4d7d-9967-84959e532fb5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Liessner, R, Dohmen, J & Wiering, M 2021, Explainable Reinforcement Learning for Longitudinal Control. in A P Rocha, L Steels & J van den Herik (eds), Proceedings of the 13th International Conference on Agents and Artificial Intelligence. ICAART 2021 , vol. 2, SciTePress, pp. 874-881, 13th International Conference on Agents and Artificial Intelligence, ICAART 2021, Virtual, Online, 04/02/2021.","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3209574120","https://openalex.org/W3107602296","https://openalex.org/W4312192474","https://openalex.org/W4210805261","https://openalex.org/W4387297750"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(DRL)":[3],"has":[4],"the":[5,9,13,56,68,75,88,96,153,173,176],"potential":[6],"to":[7,30,48,61,138,171],"surpass":[8],"existing":[10],"state":[11],"of":[12,41,58,67,77,87,104,175],"art":[14],"in":[15,107,140],"various":[16],"practical":[17],"applications.":[18],"However,":[19],"as":[20,22],"long":[21],"learned":[23,69,114,126],"strategies":[24],"and":[25,128,156],"performed":[26],"decisions":[27,174],"are":[28,45,119,159,167],"difficult":[29],"interpret,":[31],"DRL":[32,62,82],"will":[33],"not":[34],"find":[35],"its":[36],"way":[37],"into":[38],"safety-relevant":[39],"fields":[40],"application.":[42],"SHAP":[43,79,129],"values":[44,60,166],"an":[46,64,99],"approach":[47,124,170],"overcome":[49],"this":[50,73,94],"problem.":[51],"It":[52],"is":[53,83],"expected":[54],"that":[55,164],"addition":[57],"these":[59],"provides":[63],"improved":[65],"understanding":[66],"action-selection":[70],"policy.":[71],"In":[72,93],"paper,":[74],"application":[76],"a":[78,108,116,122,147,168],"method":[80],"for":[81],"demonstrated":[84],"by":[85,121],"means":[86],"OpenAI":[89],"Gym":[90],"LongiControl":[91],"Environment.":[92],"problem,":[95],"agent":[97],"drives":[98],"autonomous":[100],"vehicle":[101],"under":[102],"consideration":[103],"speed":[105],"limits":[106],"single":[109],"lane":[110],"route.":[111],"The":[112,131,161],"controls":[113],"with":[115],"DDPG":[117],"algorithm":[118],"interpreted":[120],"novel":[123],"combining":[125],"actions":[127],"values.":[130],"proposed":[132],"RL-SHAP":[133,165],"representation":[134],"makes":[135],"it":[136],"possible":[137],"observe":[139],"every":[141],"time":[142],"step":[143],"which":[144,157],"features":[145],"have":[146],"positive":[148],"or":[149],"negative":[150],"effect":[151],"on":[152],"selected":[154],"action":[155],"influences":[158],"negligible.":[160],"results":[162],"show":[163],"suitable":[169],"interpret":[172],"agent.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}