{"id":"https://openalex.org/W4285605417","doi":"https://doi.org/10.24963/ijcai.2022/650","title":"PG3: Policy-Guided Planning for Generalized Policy Generation","display_name":"PG3: Policy-Guided Planning for Generalized Policy Generation","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285605417","doi":"https://doi.org/10.24963/ijcai.2022/650"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/650","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/650","pdf_url":"https://www.ijcai.org/proceedings/2022/0650.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0650.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007480648","display_name":"Ryan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Yang","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073565150","display_name":"Tom Silver","orcid":"https://orcid.org/0000-0002-3094-0410"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Silver","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062719305","display_name":"Aidan Curtis","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aidan Curtis","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063238208","display_name":"Tom\u00e1s Lozano\u2010P\u00e9rez","orcid":"https://orcid.org/0000-0002-8657-2450"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tomas Lozano-Perez","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012862284","display_name":"Leslie Pack Kaelbling","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leslie Kaelbling","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1038,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.26610125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4686","last_page":"4692"},"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":0.9969000220298767,"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":0.9969000220298767,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9692000150680542,"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/T10050","display_name":"Multi-Criteria Decision Making","score":0.9373000264167786,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7510567903518677},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7415552139282227},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6378083825111389},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.6219692826271057},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4932841658592224},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4525640606880188},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.4263607859611511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3446418046951294},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.33559679985046387},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1145380437374115},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10165834426879883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7510567903518677},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7415552139282227},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6378083825111389},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.6219692826271057},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4932841658592224},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4525640606880188},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.4263607859611511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3446418046951294},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.33559679985046387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1145380437374115},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10165834426879883},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/650","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/650","pdf_url":"https://www.ijcai.org/proceedings/2022/0650.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/650","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/650","pdf_url":"https://www.ijcai.org/proceedings/2022/0650.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G1072749480","display_name":null,"funder_award_id":"FA9550-17","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G260750634","display_name":null,"funder_award_id":"FA9550-17-1","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G2773019091","display_name":null,"funder_award_id":"FA9550-17-1-0165","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G4406529996","display_name":null,"funder_award_id":"1723381","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5452928237","display_name":null,"funder_award_id":"N00014-18-1-2847","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G6098521345","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285605417.pdf","grobid_xml":"https://content.openalex.org/works/W4285605417.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W955033985","https://openalex.org/W1628070947","https://openalex.org/W2020149918","https://openalex.org/W2134980541","https://openalex.org/W2157340420","https://openalex.org/W2221785343","https://openalex.org/W2296450740","https://openalex.org/W2749952662","https://openalex.org/W2888241791","https://openalex.org/W2900636635","https://openalex.org/W2904811519","https://openalex.org/W2921844528","https://openalex.org/W2962730572","https://openalex.org/W2963485726","https://openalex.org/W2963548923","https://openalex.org/W2964036701","https://openalex.org/W3010796547","https://openalex.org/W3023380900","https://openalex.org/W3042392651","https://openalex.org/W3086207594","https://openalex.org/W3150583184","https://openalex.org/W4287867561","https://openalex.org/W6697322960","https://openalex.org/W6748290940","https://openalex.org/W6774041431"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W2012531322","https://openalex.org/W3083152911","https://openalex.org/W2402761219"],"abstract_inverted_index":{"A":[0],"longstanding":[1],"objective":[2],"in":[3,101,136],"classical":[4],"planning":[5,88,124],"is":[6,78,110],"to":[7,36,86],"synthesize":[8],"policies":[9,129,144],"that":[10,61,79,97,140],"generalize":[11],"across":[12],"multiple":[13],"problems":[14,91,125],"from":[15],"the":[16,32,38],"same":[17],"domain.":[18],"In":[19],"this":[20],"work,":[21],"we":[22],"study":[23,116],"generalized":[24,143],"policy":[25,50,82,121],"search-based":[26],"methods":[27],"with":[28],"a":[29,58,80,93,102,117],"focus":[30],"on":[31,89],"score":[33,47],"function":[34],"used":[35,85],"guide":[37,87],"search":[39,122],"over":[40],"policies.":[41],"We":[42,114],"demonstrate":[43],"limitations":[44],"of":[45,120],"two":[46],"functions":[48],"---":[49,55],"evaluation":[51],"and":[52,56,128,147],"plan":[53],"comparison":[54],"propose":[57],"new":[59],"approach":[60],"overcomes":[62],"these":[63],"limitations.":[64],"The":[65],"main":[66],"idea":[67],"behind":[68],"our":[69],"approach,":[70],"Policy-Guided":[71],"Planning":[72],"for":[73,95],"Generalized":[74],"Policy":[75],"Generalization":[76],"(PG3),":[77],"candidate":[81],"should":[83],"be":[84],"training":[90],"as":[92],"mechanism":[94],"evaluating":[96],"candidate.":[98],"Theoretical":[99],"results":[100,135],"simplified":[103],"setting":[104],"give":[105],"conditions":[106],"under":[107],"which":[108],"PG3":[109,141],"optimal":[111],"or":[112],"admissible.":[113],"then":[115],"specific":[118],"instantiation":[119],"where":[123],"are":[126,130],"PDDL-based":[127],"lifted":[131],"decision":[132],"lists.":[133],"Empirical":[134],"six":[137],"domains":[138],"confirm":[139],"learns":[142],"more":[145],"efficiently":[146],"effectively":[148],"than":[149],"several":[150],"baselines.":[151]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
