{"id":"https://openalex.org/W4319659130","doi":"https://doi.org/10.1007/s00521-023-08211-x","title":"Graph learning-based generation of abstractions for reinforcement learning","display_name":"Graph learning-based generation of abstractions for reinforcement learning","publication_year":2023,"publication_date":"2023-02-09","ids":{"openalex":"https://openalex.org/W4319659130","doi":"https://doi.org/10.1007/s00521-023-08211-x"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-023-08211-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-08211-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-08211-x.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-08211-x.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011726289","display_name":"Yuan Xue","orcid":"https://orcid.org/0000-0003-1773-6682"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Yuan Xue","raw_affiliation_strings":["L3S Research Centre, Leibniz University Hannover, Lange Laube 6, Hannover, 30167, Lower Saxony, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1773-6682","affiliations":[{"raw_affiliation_string":"L3S Research Centre, Leibniz University Hannover, Lange Laube 6, Hannover, 30167, Lower Saxony, Germany","institution_ids":["https://openalex.org/I4210136150","https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009587907","display_name":"Daniel Kudenko\u22c6","orcid":"https://orcid.org/0000-0003-3359-3255"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Kudenko","raw_affiliation_strings":["L3S Research Centre, Leibniz University Hannover, Lange Laube 6, Hannover, 30167, Lower Saxony, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Centre, Leibniz University Hannover, Lange Laube 6, Hannover, 30167, Lower Saxony, Germany","institution_ids":["https://openalex.org/I4210136150","https://openalex.org/I114112103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027689420","display_name":"Megha Khosla","orcid":"https://orcid.org/0000-0002-0319-3181"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Megha Khosla","raw_affiliation_strings":["Intelligent Systems Department, Delft University of Technology, Van Mourik Broekmanweg 6, 2628 XE, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems Department, Delft University of Technology, Van Mourik Broekmanweg 6, 2628 XE, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011726289"],"corresponding_institution_ids":["https://openalex.org/I114112103","https://openalex.org/I4210136150"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.16,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.48644532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"37","issue":"19","first_page":"13187","last_page":"13207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9851999878883362,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9377999901771545,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8270705938339233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7943662405014038},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7065075039863586},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5880091786384583},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5053501725196838},{"id":"https://openalex.org/keywords/combinatorial-explosion","display_name":"Combinatorial explosion","score":0.49487537145614624},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.48962336778640747},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47169163823127747},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4612928628921509},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4544835090637207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44768452644348145},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4411587417125702},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4342110753059387},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4291975796222687},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.412826269865036},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40469563007354736},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.356082946062088},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1305537223815918}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8270705938339233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943662405014038},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7065075039863586},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5880091786384583},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5053501725196838},{"id":"https://openalex.org/C115908005","wikidata":"https://www.wikidata.org/wiki/Q2668364","display_name":"Combinatorial explosion","level":2,"score":0.49487537145614624},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.48962336778640747},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47169163823127747},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4612928628921509},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4544835090637207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44768452644348145},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4411587417125702},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4342110753059387},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4291975796222687},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.412826269865036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40469563007354736},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.356082946062088},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1305537223815918},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s00521-023-08211-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-08211-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-08211-x.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},{"id":"pmh:oai:www.repo.uni-hannover.de:123456789/15534","is_oa":true,"landing_page_url":"https://www.repo.uni-hannover.de/handle/123456789/15534","pdf_url":"https://www.repo.uni-hannover.de/bitstream/123456789/15534/1/s00521-023-08211-x-1.pdf","source":{"id":"https://openalex.org/S4306401574","display_name":"Institutional Repository of Leibniz Universit\u00e4t Hannover (Leibniz Universit\u00e4t Hannover)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114112103","host_organization_name":"Leibniz University Hannover","host_organization_lineage":["https://openalex.org/I114112103"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Neural Computing and Applications 2023 (2023)","raw_type":"doc-type:Article"},{"id":"pmh:oai:tudelft.nl:uuid:36241f30-efc5-45c4-884c-38574aadd49d","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:36241f30-efc5-45c4-884c-38574aadd49d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},{"id":"doi:10.15488/15413","is_oa":true,"landing_page_url":"https://doi.org/10.15488/15413","pdf_url":null,"source":{"id":"https://openalex.org/S7407052956","display_name":"Leibniz Universit\u00e4t Hannover","issn_l":null,"issn":[],"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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1007/s00521-023-08211-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-08211-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-08211-x.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5}],"awards":[{"id":"https://openalex.org/G367552324","display_name":"Internationales Leibniz Zukunftslabor K\u00fcnstliche Intelligenz","funder_award_id":"01DD20003","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320322379","display_name":"Gottfried Wilhelm Leibniz Universit\u00e4t Hannover","ror":"https://ror.org/0304hq317"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319659130.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1556824961","https://openalex.org/W1981096006","https://openalex.org/W1985756506","https://openalex.org/W1988821219","https://openalex.org/W1995688924","https://openalex.org/W2056354534","https://openalex.org/W2079247031","https://openalex.org/W2081944499","https://openalex.org/W2109910161","https://openalex.org/W2111316871","https://openalex.org/W2116341502","https://openalex.org/W2154851992","https://openalex.org/W2158969944","https://openalex.org/W2160808139","https://openalex.org/W2387462954","https://openalex.org/W2575705757","https://openalex.org/W2596874484","https://openalex.org/W2605234117","https://openalex.org/W2606126444","https://openalex.org/W2962756421","https://openalex.org/W3032600838","https://openalex.org/W3090555890","https://openalex.org/W3104097132","https://openalex.org/W3168892396","https://openalex.org/W4246262524","https://openalex.org/W6600120041","https://openalex.org/W6600341879","https://openalex.org/W6600874529","https://openalex.org/W6610763331","https://openalex.org/W6832756385"],"related_works":["https://openalex.org/W2097562045","https://openalex.org/W2807018115","https://openalex.org/W4200250224","https://openalex.org/W2285658092","https://openalex.org/W4388236136","https://openalex.org/W2126560268","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532","https://openalex.org/W1996326480"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"application":[2],"of":[3,15,70,95,107,122,147,159,169],"reinforcement":[4],"learning":[5,84],"(RL)":[6],"algorithms":[7],"is":[8,79],"often":[9],"hindered":[10],"by":[11,41,81],"the":[12,16,37,67,90,96,139,148,157,164,170],"combinatorial":[13],"explosion":[14],"state":[17,27],"space.":[18],"Previous":[19],"works":[20],"have":[21],"leveraged":[22],"abstractions":[23,38],"which":[24],"condense":[25],"large":[26],"spaces":[28],"to":[29,53,65,75,124,132,154,162],"find":[30],"tractable":[31],"solutions.":[32],"However,":[33],"they":[34],"assumed":[35],"that":[36],"are":[39,152],"provided":[40],"a":[42,50,105],"domain":[43],"expert.":[44],"In":[45],"this":[46],"work,":[47],"we":[48,151],"propose":[49],"new":[51],"approach":[52,74,119,161],"automatically":[54],"construct":[55],"abstract":[56,77],"Markov":[57],"decision":[58],"processes":[59],"(AMDPs)":[60],"for":[61],"potential-based":[62],"reward":[63,93,167],"shaping":[64],"improve":[66],"sample":[68,128],"efficiency":[69,129],"RL":[71],"algorithms.":[72],"Our":[73,118],"constructing":[76],"states":[78],"inspired":[80],"graph":[82],"representation":[83],"methods":[85],",":[86],"it":[87],"effectively":[88],"encodes":[89],"topological":[91,165],"and":[92,109,115,130,166],"structure":[94,168],"ground-level":[97,171],"MDP.":[98,172],"We":[99],"perform":[100],"large-scale":[101],"quantitative":[102],"experiments":[103],"on":[104],"range":[106],"navigation":[108],"gathering":[110],"tasks":[111],"under":[112],"both":[113],"stationary":[114],"stochastic":[116],"settings.":[117],"shows":[120],"improvements":[121],"up":[123,131],"8.5":[125],"times":[126,134],"in":[127,135],"3":[133],"run":[136],"time":[137],"over":[138],"baseline":[140],"approach.":[141],"Besides,":[142],"with":[143],"our":[144,160],"qualitative":[145],"analyses":[146],"generated":[149],"AMDPs,":[150],"able":[153],"visually":[155],"demonstrate":[156],"capability":[158],"preserve":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}