{"id":"https://openalex.org/W2899455150","doi":"https://doi.org/10.1609/aaai.v33i01.33012970","title":"SDRL: Interpretable and Data-Efficient Deep Reinforcement Learning Leveraging Symbolic Planning","display_name":"SDRL: Interpretable and Data-Efficient Deep Reinforcement Learning Leveraging Symbolic Planning","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2899455150","doi":"https://doi.org/10.1609/aaai.v33i01.33012970","mag":"2899455150"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33012970","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33012970","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4153/4031","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4153/4031","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025744129","display_name":"Daoming Lyu","orcid":"https://orcid.org/0000-0003-2625-9865"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daoming Lyu","raw_affiliation_strings":["Auburn University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564849","display_name":"Fangkai Yang","orcid":"https://orcid.org/0000-0002-3089-0345"},"institutions":[{"id":"https://openalex.org/I4210089311","display_name":"Yanan University Affiliated Hospital","ror":"https://ror.org/006992e45","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210089311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangkai Yang","raw_affiliation_strings":["Maana Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maana Inc","institution_ids":["https://openalex.org/I4210089311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461752","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0003-4006-1126"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Auburn University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109278826","display_name":"Steven Gustafson","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089311","display_name":"Yanan University Affiliated Hospital","ror":"https://ror.org/006992e45","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210089311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Steven Gustafson","raw_affiliation_strings":["Maana Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maana Inc","institution_ids":["https://openalex.org/I4210089311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":99,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"2970","last_page":"2977"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9829000234603882,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9829000234603882,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9656999707221985,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9085999727249146,"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/interpretability","display_name":"Interpretability","score":0.9310362339019775},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8398000001907349},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7190970182418823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6116194128990173},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.5920531153678894},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5053487420082092}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9310362339019775},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8398000001907349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190970182418823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6116194128990173},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.5920531153678894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5053487420082092}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33012970","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33012970","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4153/4031","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4153","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33012970","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33012970","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4153/4031","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2899455150.pdf","grobid_xml":"https://content.openalex.org/works/W2899455150.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1549353711","https://openalex.org/W1605439581","https://openalex.org/W1855398616","https://openalex.org/W1903938722","https://openalex.org/W2000514530","https://openalex.org/W2049791401","https://openalex.org/W2101915445","https://openalex.org/W2109910161","https://openalex.org/W2139612737","https://openalex.org/W2145339207","https://openalex.org/W2149280200","https://openalex.org/W2155968351","https://openalex.org/W2158548602","https://openalex.org/W2170655684","https://openalex.org/W2201581102","https://openalex.org/W2335959470","https://openalex.org/W2516809705","https://openalex.org/W2518731509","https://openalex.org/W2578289159","https://openalex.org/W2586777479","https://openalex.org/W2594475271","https://openalex.org/W2742143911","https://openalex.org/W2746553466","https://openalex.org/W2765308067","https://openalex.org/W2798713496","https://openalex.org/W2807015674","https://openalex.org/W2807193538","https://openalex.org/W2950040888","https://openalex.org/W2952509347","https://openalex.org/W2963262099","https://openalex.org/W2963709735","https://openalex.org/W3101355526","https://openalex.org/W3103780890","https://openalex.org/W4294624294","https://openalex.org/W4295837424","https://openalex.org/W4394654451","https://openalex.org/W6683443546","https://openalex.org/W6684906258","https://openalex.org/W6749972507","https://openalex.org/W6786039469","https://openalex.org/W7075606714"],"related_works":["https://openalex.org/W1986582023","https://openalex.org/W2883749686","https://openalex.org/W2961085424","https://openalex.org/W2966829450","https://openalex.org/W4315864862","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3209574120"],"abstract_inverted_index":{"Deep":[0,70],"reinforcement":[1,149],"learning":[2,9,150],"(DRL)":[3],"has":[4],"gained":[5],"great":[6],"success":[7],"by":[8,89],"directly":[10,151],"from":[11,152],"high-dimensional":[12,78,154],"sensory":[13,79,155],"inputs,":[14],"yet":[15],"is":[16,27,87],"notorious":[17],"for":[18],"the":[19,25,35,43,48,52,133,138,160],"lack":[20],"of":[21,24,37,51,68,107,140,162],"interpretability.":[22],"Interpretability":[23],"subtasks":[26],"critical":[28],"in":[29],"hierarchical":[30],"decision-making":[31],"as":[32],"it":[33],"increases":[34],"transparency":[36],"black-box-style":[38],"DRL":[39,63],"approach":[40],"and":[41,64,81,113,123,147],"helps":[42],"RL":[44],"practitioners":[45],"to":[46,93,126],"understand":[47],"high-level":[49],"behavior":[50],"system":[53],"better.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58],"introduce":[59],"symbolic":[60,82,91,129,145],"planning":[61,142],"into":[62],"propose":[65],"a":[66,97,153],"framework":[67,95],"Symbolic":[69],"Reinforcement":[71],"Learning":[72],"(SDRL)":[73],"that":[74],"can":[75],"handle":[76],"both":[77],"inputs":[80],"planning.":[83],"The":[84,117],"task-level":[85],"interpretability":[86,161],"enabled":[88],"relating":[90],"actions":[92],"options.This":[94],"features":[96],"planner":[98],"\u2013":[99,101],"controller":[100],"meta-controller":[102],"architecture,":[103],"which":[104],"takes":[105],"charge":[106],"subtask":[108,111,114],"scheduling,":[109],"data-driven":[110],"learning,":[112],"evaluation,":[115],"respectively.":[116],"three":[118],"components":[119],"cross-fertilize":[120],"each":[121],"other":[122],"eventually":[124],"converge":[125],"an":[127],"optimal":[128],"plan":[130],"along":[131,164],"with":[132,144,165,170],"learned":[134],"subtasks,":[135,163],"bringing":[136],"together":[137],"advantages":[139],"long-term":[141],"capability":[143],"knowledge":[146],"end-to-end":[148],"input.":[156],"Experimental":[157],"results":[158],"validate":[159],"improved":[166],"data":[167],"efficiency":[168],"compared":[169],"state-of-the-art":[171],"approaches.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}