{"id":"https://openalex.org/W4385439232","doi":"https://doi.org/10.24963/kr.2023/21","title":"Learning Hierarchical Policies by Iteratively Reducing the Width of Sketch Rules","display_name":"Learning Hierarchical Policies by Iteratively Reducing the Width of Sketch Rules","publication_year":2023,"publication_date":"2023-07-31","ids":{"openalex":"https://openalex.org/W4385439232","doi":"https://doi.org/10.24963/kr.2023/21"},"language":"en","primary_location":{"id":"doi:10.24963/kr.2023/21","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/kr.2023/21","pdf_url":"https://proceedings.kr.org/2023/21/kr2023-0021-drexler-et-al.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth International Conference on Principles of Knowledge Representation and Reasoning","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://proceedings.kr.org/2023/21/kr2023-0021-drexler-et-al.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022936950","display_name":"Dominik Drexler","orcid":"https://orcid.org/0000-0002-1350-2144"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Dominik Drexler","raw_affiliation_strings":["Link\u00f6ping University"],"affiliations":[{"raw_affiliation_string":"Link\u00f6ping University","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031089257","display_name":"Jendrik Seipp","orcid":"https://orcid.org/0000-0002-2498-8020"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jendrik Seipp","raw_affiliation_strings":["Link\u00f6ping University"],"affiliations":[{"raw_affiliation_string":"Link\u00f6ping University","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046427368","display_name":"H\u00e9ctor Geffner","orcid":"https://orcid.org/0000-0001-9851-8219"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]},{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE","SE"],"is_corresponding":false,"raw_author_name":"Hector Geffner","raw_affiliation_strings":["Link\u00f6ping University","RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"Link\u00f6ping University","institution_ids":["https://openalex.org/I102134673"]},{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022936950"],"corresponding_institution_ids":["https://openalex.org/I102134673"],"apc_list":null,"apc_paid":null,"fwci":1.037,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81110644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"208","last_page":"218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9954000115394592,"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":0.9771999716758728,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.8971364498138428},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.756224513053894},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7191307544708252},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6377361416816711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5498754978179932},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.529380738735199},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.43652844429016113},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4175108075141907},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3984553813934326},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3295166492462158},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1642041802406311},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13373109698295593}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.8971364498138428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756224513053894},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7191307544708252},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6377361416816711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5498754978179932},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.529380738735199},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.43652844429016113},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4175108075141907},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3984553813934326},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3295166492462158},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1642041802406311},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13373109698295593},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/kr.2023/21","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/kr.2023/21","pdf_url":"https://proceedings.kr.org/2023/21/kr2023-0021-drexler-et-al.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth International Conference on Principles of Knowledge Representation and Reasoning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/kr.2023/21","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/kr.2023/21","pdf_url":"https://proceedings.kr.org/2023/21/kr2023-0021-drexler-et-al.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth International Conference on Principles of Knowledge Representation and Reasoning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G1364868472","display_name":null,"funder_award_id":"2018-05973","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G1783795302","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G3165808449","display_name":null,"funder_award_id":"022-06725","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G3321450376","display_name":null,"funder_award_id":"05973","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G4493597635","display_name":null,"funder_award_id":"NAISS","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G5356226767","display_name":null,"funder_award_id":"2018-0597","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G6625919268","display_name":null,"funder_award_id":"2018-05973","funder_id":"https://openalex.org/F4320322225","funder_display_name":"Link\u00f6pings Universitet"},{"id":"https://openalex.org/G712881263","display_name":null,"funder_award_id":"2018-","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G8338695050","display_name":null,"funder_award_id":"2022-0672","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G8436673617","display_name":null,"funder_award_id":"2022-06725","funder_id":"https://openalex.org/F4320322225","funder_display_name":"Link\u00f6pings Universitet"},{"id":"https://openalex.org/G8869864247","display_name":null,"funder_award_id":"2022-06725","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320308269","display_name":"Alexander von Humboldt-Stiftung","ror":"https://ror.org/012kf4317"},{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320322225","display_name":"Link\u00f6pings Universitet","ror":"https://ror.org/05ynxx418"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385439232.pdf"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W92128319","https://openalex.org/W125130877","https://openalex.org/W1528049422","https://openalex.org/W1981627423","https://openalex.org/W1996913161","https://openalex.org/W2055486654","https://openalex.org/W2100988719","https://openalex.org/W2109827621","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2138494816","https://openalex.org/W2143435603","https://openalex.org/W2158548602","https://openalex.org/W2169173532","https://openalex.org/W2210368431","https://openalex.org/W2279668280","https://openalex.org/W2563461029","https://openalex.org/W2592215206","https://openalex.org/W2605098186","https://openalex.org/W2785422319","https://openalex.org/W2900636635","https://openalex.org/W2904811519","https://openalex.org/W2921844528","https://openalex.org/W2950040888","https://openalex.org/W2962730572","https://openalex.org/W2963234253","https://openalex.org/W2963485726","https://openalex.org/W2996622139","https://openalex.org/W3092156990","https://openalex.org/W3106271432","https://openalex.org/W3106612030","https://openalex.org/W3124088494","https://openalex.org/W3146347964","https://openalex.org/W3174761502","https://openalex.org/W3175830949","https://openalex.org/W3176184692","https://openalex.org/W3176369502","https://openalex.org/W3189872547","https://openalex.org/W3199180040","https://openalex.org/W4254300114","https://openalex.org/W4280581442","https://openalex.org/W4288046092","https://openalex.org/W4312425102","https://openalex.org/W6605075745","https://openalex.org/W6645670200","https://openalex.org/W6675301218","https://openalex.org/W6676330250","https://openalex.org/W6680716285","https://openalex.org/W6683443546","https://openalex.org/W6688197206","https://openalex.org/W6738388615","https://openalex.org/W6894073420","https://openalex.org/W6950583753","https://openalex.org/W6969021483","https://openalex.org/W7075606714"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W4299685261","https://openalex.org/W2964266708","https://openalex.org/W2797225766","https://openalex.org/W4310562451","https://openalex.org/W4390872497"],"abstract_inverted_index":{"Hierarchical":[0],"policies":[1,66,164,179],"are":[2,104],"a":[3,20,27,60,93,134,143],"key":[4],"ingredient":[5],"of":[6,13,19,108,118,145],"intelligent":[7],"behavior,":[8],"expressing":[9],"the":[10,17,41,90,112,116,125,139,150],"different":[11],"levels":[12],"abstraction":[14],"involved":[15],"in":[16,47,180],"solution":[18],"problem.":[21],"Learning":[22],"hierarchical":[23,65,152,163],"policies,":[24,153],"however,":[25],"remains":[26],"challenge,":[28],"as":[29,96],"no":[30,72],"general":[31,135,178],"learning":[32,51,64,82,140,162,166,176],"principles":[33],"have":[34,92,129],"been":[35],"identified":[36],"for":[37,63,114],"this":[38,56],"purpose,":[39],"despite":[40],"broad":[42],"interest":[43],"and":[44,52,102,111,132,154,167],"vast":[45],"literature":[46],"both":[48],"model-free":[49],"reinforcement":[50],"model-based":[53],"planning.":[54],"In":[55],"work,":[57],"we":[58],"introduce":[59],"principled":[61],"method":[62,78,141],"over":[67],"classical":[68,146],"planning":[69,147],"domains,":[70,148],"with":[71],"supervision":[73],"from":[74],"small":[75],"instances.":[76],"The":[77],"is":[79,121,171],"based":[80],"on":[81,142],"to":[83],"decompose":[84],"problems":[85],"into":[86],"subproblems":[87,91,103],"so":[88],"that":[89,161],"lower":[94],"complexity":[95],"measured":[97],"by":[98,106,165],"their":[99,156],"width.":[100],"Problems":[101],"captured":[105],"means":[107],"sketch":[109,119,127],"rules,":[110],"scheme":[113],"reducing":[115],"width":[117,131],"rules":[120,128],"applied":[122],"iteratively":[123,170],"until":[124],"final":[126],"zero":[130],"encode":[133],"policy.":[136],"We":[137,158],"evaluate":[138],"number":[144],"analyze":[149],"resulting":[151],"prove":[155],"properties.":[157],"also":[159],"show":[160],"refining":[168],"sketches":[169],"often":[172],"more":[173],"efficient":[174],"than":[175],"flat":[177],"one":[181],"shot.":[182]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}