{"id":"https://openalex.org/W4385438429","doi":"https://doi.org/10.24963/kr.2023/63","title":"Learning General Policies with Policy Gradient Methods","display_name":"Learning General Policies with Policy Gradient Methods","publication_year":2023,"publication_date":"2023-07-31","ids":{"openalex":"https://openalex.org/W4385438429","doi":"https://doi.org/10.24963/kr.2023/63"},"language":"en","primary_location":{"id":"doi:10.24963/kr.2023/63","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/kr.2023/63","pdf_url":"https://proceedings.kr.org/2023/63/kr2023-0063-stahlberg-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/2023/63/kr2023-0063-stahlberg-et-al.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063877302","display_name":"Simon St\u00e5hlberg","orcid":"https://orcid.org/0000-0002-4092-8175"},"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":"Simon St\u00e5hlberg","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/A5010562834","display_name":"Blai Bonet","orcid":null},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Blai Bonet","raw_affiliation_strings":["Universitat Pompeu Fabra"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]}]},{"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":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063877302"],"corresponding_institution_ids":["https://openalex.org/I102134673"],"apc_list":null,"apc_paid":null,"fwci":1.5555,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86232088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"647","last_page":"657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9886000156402588,"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":0.9886000156402588,"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":0.9818000197410583,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9664000272750854,"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":0.8490492105484009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7304203510284424},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.669318437576294},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.664608359336853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6481519341468811},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5448706746101379},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5010755062103271},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46700581908226013},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4203872084617615},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3628486096858978},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13740050792694092}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8490492105484009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304203510284424},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.669318437576294},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.664608359336853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6481519341468811},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5448706746101379},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5010755062103271},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46700581908226013},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4203872084617615},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3628486096858978},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13740050792694092},{"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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/kr.2023/63","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/kr.2023/63","pdf_url":"https://proceedings.kr.org/2023/63/kr2023-0063-stahlberg-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.2023/63","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/kr.2023/63","pdf_url":"https://proceedings.kr.org/2023/63/kr2023-0063-stahlberg-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":[],"awards":[{"id":"https://openalex.org/G1174531324","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320322327","funder_display_name":"Knut och Alice Wallenbergs Stiftelse"},{"id":"https://openalex.org/G3203446764","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320322327","funder_display_name":"Knut och Alice Wallenbergs Stiftelse"},{"id":"https://openalex.org/G8683756101","display_name":null,"funder_award_id":"support","funder_id":"https://openalex.org/F4320322327","funder_display_name":"Knut och Alice Wallenbergs Stiftelse"}],"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/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320336380","display_name":"National Supercomputer Centre, Link\u00f6pings Universitet","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385438429.pdf"},"referenced_works_count":94,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W92128319","https://openalex.org/W1522301498","https://openalex.org/W1967346767","https://openalex.org/W1987411046","https://openalex.org/W1993411524","https://openalex.org/W2030888056","https://openalex.org/W2070878381","https://openalex.org/W2096600060","https://openalex.org/W2098432798","https://openalex.org/W2116341502","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2156737235","https://openalex.org/W2169173532","https://openalex.org/W2296450740","https://openalex.org/W2479648088","https://openalex.org/W2531891978","https://openalex.org/W2563461029","https://openalex.org/W2579750028","https://openalex.org/W2736601468","https://openalex.org/W2739712182","https://openalex.org/W2749952662","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2900636635","https://openalex.org/W2902907165","https://openalex.org/W2904811519","https://openalex.org/W2907923173","https://openalex.org/W2917056950","https://openalex.org/W2934382939","https://openalex.org/W2960567166","https://openalex.org/W2962730572","https://openalex.org/W2963548923","https://openalex.org/W2964544903","https://openalex.org/W2966453711","https://openalex.org/W2990366588","https://openalex.org/W2991286286","https://openalex.org/W2994073215","https://openalex.org/W2994943647","https://openalex.org/W2996471083","https://openalex.org/W3005700790","https://openalex.org/W3011651653","https://openalex.org/W3023380900","https://openalex.org/W3029947299","https://openalex.org/W3036282537","https://openalex.org/W3037740263","https://openalex.org/W3037871539","https://openalex.org/W3042392651","https://openalex.org/W3048593389","https://openalex.org/W3099954417","https://openalex.org/W3100366369","https://openalex.org/W3101355526","https://openalex.org/W3123212791","https://openalex.org/W3134315323","https://openalex.org/W3135588948","https://openalex.org/W3145915828","https://openalex.org/W3165317800","https://openalex.org/W3175830949","https://openalex.org/W3176138766","https://openalex.org/W3177995633","https://openalex.org/W3189872547","https://openalex.org/W3194856818","https://openalex.org/W3200538762","https://openalex.org/W3206618065","https://openalex.org/W3216772467","https://openalex.org/W4226278401","https://openalex.org/W4237284205","https://openalex.org/W4280581442","https://openalex.org/W4283694818","https://openalex.org/W4286792256","https://openalex.org/W4287866775","https://openalex.org/W4288046092","https://openalex.org/W4288257146","https://openalex.org/W4288956373","https://openalex.org/W4295312788","https://openalex.org/W4299591165","https://openalex.org/W4312330985","https://openalex.org/W4312425102","https://openalex.org/W4315487473","https://openalex.org/W6631190155","https://openalex.org/W6642082902","https://openalex.org/W6648914341","https://openalex.org/W6677316912","https://openalex.org/W6677916085","https://openalex.org/W6682849425","https://openalex.org/W6683195989","https://openalex.org/W6721692139","https://openalex.org/W6741002519","https://openalex.org/W6774858212","https://openalex.org/W6783827371","https://openalex.org/W6784882484","https://openalex.org/W6786039469","https://openalex.org/W6794086348"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W2011430815","https://openalex.org/W4321606653"],"abstract_inverted_index":{"While":[0],"reinforcement":[1,82,228],"learning":[2,83,113,226,229],"methods":[3,101,180,215,266],"have":[4,56,220],"delivered":[5],"remarkable":[6],"results":[7],"in":[8,22,40,86,118,167,174,252],"a":[9,23,30,53,119],"number":[10],"of":[11,34,52,64,206,212,238,256],"settings,":[12],"generalization,":[13],"i.e.,":[14],"the":[15,77,123,145,200,204,210,213,217,234,241,263],"ability":[16],"to":[17,68,75,94,142,154,184,222,276],"produce":[18],"policies":[19,46,96,127,186,248],"that":[20,47,97,178,187],"generalize":[21,48,98,188],"reliable":[24],"and":[25,85,111,115,138,166,203,231,240,245,271],"systematic":[26],"way,":[27],"has":[28,36],"remained":[29],"challenge.":[31],"The":[32,62],"problem":[33],"generalization":[35,246],"been":[37,57],"addressed":[38,260],"formally":[39],"classical":[41],"planning":[42,164],"where":[43],"provable":[44],"correct":[45],"over":[49,163],"all":[50],"instances":[51],"given":[54],"domain":[55],"learned":[58,107],"using":[59,195],"combinatorial":[60,100,110,196],"methods.":[61],"aim":[63],"this":[65],"work":[66],"is":[67],"bring":[69],"these":[70,172,257],"two":[71],"research":[72],"threads":[73],"together":[74],"illuminate":[76],"conditions":[78],"under":[79],"which":[80],"(deep)":[81],"approaches,":[84,114],"particular,":[87],"policy":[88],"optimization":[89],"methods,":[90],"can":[91,181],"be":[92,182,250],"used":[93,183],"learn":[95,185],"like":[99],"do.":[102],"We":[103],"draw":[104],"on":[105,216],"lessons":[106],"from":[108,140,233],"previous":[109],"deep":[112,225],"extend":[116],"them":[117],"convenient":[120],"way.":[121],"From":[122,144],"former,":[124],"we":[125,147,176],"model":[126],"as":[128,132,190,192],"state":[129],"transition":[130],"classifiers,":[131],"(ground)":[133],"actions":[134],"are":[135,259],"not":[136],"general":[137],"change":[139],"instance":[141],"instance.":[143],"latter,":[146],"use":[148,205],"graph":[149],"neural":[150],"networks":[151],"(GNNs)":[152],"adapted":[153],"deal":[155],"with":[156,224],"relational":[157],"structures":[158],"for":[159],"representing":[160],"value":[161],"functions":[162],"states,":[165],"our":[168],"case,":[169],"policies.":[170],"With":[171],"ingredients":[173],"place,":[175],"find":[177],"actor-critic":[179],"almost":[189],"well":[191],"those":[193],"obtained":[194],"approaches":[197],"while":[198],"avoiding":[199],"scalability":[201],"bottleneck":[202],"feature":[207],"pools.":[208],"Moreover,":[209],"limitations":[211,237,258],"DRL":[214,265],"benchmarks":[218],"considered":[219],"little":[221],"do":[223],"or":[227],"algorithms,":[230],"result":[232],"well-understood":[235],"expressive":[236],"GNNs,":[239],"tradeoff":[242],"between":[243],"optimality":[244],"(general":[247],"cannot":[249],"optimal":[251],"some":[253],"domains).":[254],"Both":[255],"without":[261],"changing":[262],"basic":[264],"by":[267],"adding":[268],"derived":[269],"predicates":[270],"an":[272],"alternative":[273],"cost":[274],"structure":[275],"optimize.":[277]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}