{"id":"https://openalex.org/W3034377858","doi":"https://doi.org/10.24963/ijcai.2020/304","title":"Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning","display_name":"Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034377858","doi":"https://doi.org/10.24963/ijcai.2020/304","mag":"3034377858"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/304","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/304","pdf_url":"https://www.ijcai.org/proceedings/2020/0304.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0304.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003539654","display_name":"Dieqiao Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dieqiao Feng","raw_affiliation_strings":["Cornell University","Department of Computer Science Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Department of Computer Science Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069030030","display_name":"Carla P. Gomes","orcid":"https://orcid.org/0000-0002-4441-7225"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carla Gomes","raw_affiliation_strings":["Cornell University","Department of Computer Science Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Department of Computer Science Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105461279","display_name":"Bart Selman","orcid":"https://orcid.org/0000-0003-0666-3123"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bart Selman","raw_affiliation_strings":["Cornell University","Department of Computer Science Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Department of Computer Science Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2198","last_page":"2205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9987000226974487,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9987000226974487,"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/T10260","display_name":"Software Engineering Research","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.7889318466186523},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7668207883834839},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7650316953659058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6419553756713867},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6332720518112183},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5779094696044922},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.5540286898612976},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.4946920573711395},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4529026448726654},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44197922945022583},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10327062010765076},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06812912225723267}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7889318466186523},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7668207883834839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7650316953659058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6419553756713867},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6332720518112183},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5779094696044922},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.5540286898612976},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4946920573711395},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4529026448726654},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44197922945022583},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10327062010765076},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06812912225723267},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/304","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/304","pdf_url":"https://www.ijcai.org/proceedings/2020/0304.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/304","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/304","pdf_url":"https://www.ijcai.org/proceedings/2020/0304.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8202728730","display_name":null,"funder_award_id":"W911NF-17-1-0187","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8626354529","display_name":null,"funder_award_id":"CCF-1522054","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034377858.pdf","grobid_xml":"https://content.openalex.org/works/W3034377858.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W946252087","https://openalex.org/W1498154961","https://openalex.org/W1555005026","https://openalex.org/W1555515018","https://openalex.org/W1667614912","https://openalex.org/W1972876322","https://openalex.org/W2025460523","https://openalex.org/W2036722182","https://openalex.org/W2044560939","https://openalex.org/W2061146398","https://openalex.org/W2097083865","https://openalex.org/W2111224220","https://openalex.org/W2147277731","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2507218956","https://openalex.org/W2732054432","https://openalex.org/W2772709170","https://openalex.org/W2963548923","https://openalex.org/W4293396018","https://openalex.org/W4298857966"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W1583422155","https://openalex.org/W1649619740","https://openalex.org/W3213252596","https://openalex.org/W1534006406","https://openalex.org/W2165071883"],"abstract_inverted_index":{"Despite":[0],"significant":[1],"progress":[2],"in":[3],"general":[4],"AI":[5,15,33,120],"planning,":[6],"certain":[7],"domains":[8,30],"remain":[9],"out":[10],"of":[11,13,27,74],"reach":[12],"current":[14,32],"planning":[16,22,121],"systems.":[17],"Sokoban":[18],"is":[19,63],"a":[20,60,113,124],"PSPACE-complete":[21],"task":[23],"and":[24],"represents":[25],"one":[26,66,72],"the":[28,44,64],"hardest":[29],"for":[31,116],"planners.":[34],"Even":[35],"domain-specific":[36],"specialized":[37],"search":[38,46],"methods":[39],"fail":[40],"quickly":[41],"due":[42],"to":[43,67,91],"exponential":[45],"complexity":[47],"on":[48,54],"hard":[49,69],"instances.":[50],"Our":[51,106],"approach":[52,101],"based":[53],"deep":[55,110],"reinforcement":[56],"learning":[57],"augmented":[58],"with":[59],"curriculum-driven":[61],"method":[62],"first":[65],"solve":[68,81],"instances":[70,83],"within":[71,84],"day":[73],"training":[75,126],"while":[76],"other":[77],"modern":[78],"solvers":[79],"cannot":[80],"these":[82],"any":[85],"reasonable":[86],"time":[87],"limit.":[88],"In":[89],"contrast":[90],"prior":[92],"efforts,":[93],"which":[94],"use":[95],"carefully":[96],"handcrafted":[97],"pruning":[98],"techniques,":[99],"our":[100],"automatically":[102],"uncovers":[103],"domain":[104],"structure.":[105],"results":[107],"reveal":[108],"that":[109],"RL":[111],"provides":[112],"promising":[114],"framework":[115],"solving":[117],"previously":[118],"unsolved":[119],"problems,":[122],"provided":[123],"proper":[125],"curriculum":[127],"can":[128],"be":[129],"devised.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}