{"id":"https://openalex.org/W4400966321","doi":"https://doi.org/10.1613/jair.1.14063","title":"Symbolic Task Inference in Deep Reinforcement Learning","display_name":"Symbolic Task Inference in Deep Reinforcement Learning","publication_year":2024,"publication_date":"2024-07-23","ids":{"openalex":"https://openalex.org/W4400966321","doi":"https://doi.org/10.1613/jair.1.14063"},"language":"en","primary_location":{"id":"doi:10.1613/jair.1.14063","doi":"https://doi.org/10.1613/jair.1.14063","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.14063","pdf_url":"https://www.jair.org/index.php/jair/article/download/14063/27062","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","doaj","dongbi-b","erih-plus","jufo-3","norway-2","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jair.org/index.php/jair/article/download/14063/27062","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033668003","display_name":"Hosein Hasanbeig","orcid":"https://orcid.org/0000-0002-1715-9830","observed_orcids":["https://orcid.org/0000-0002-1715-9830"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hosein Hasanbeig","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102706624","display_name":"Natasha Yogananda Jeppu","orcid":"https://orcid.org/0000-0002-3676-1843","observed_orcids":["https://orcid.org/0000-0002-3676-1843"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Natasha Yogananda Jeppu","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091718585","display_name":"Alessandro Abate","orcid":"https://orcid.org/0000-0002-5627-9093","observed_orcids":["https://orcid.org/0000-0002-5627-9093","https://orcid.org/0000-0002-7767-2935"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alessandro Abate","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015518667","display_name":"Tom Melham","orcid":"https://orcid.org/0000-0002-2462-2782","observed_orcids":["https://orcid.org/0000-0002-2462-2782"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tom Melham","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086206346","display_name":"Daniel Kroening","orcid":"https://orcid.org/0000-0002-6681-5283","observed_orcids":["https://orcid.org/0000-0002-6681-5283"]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Kroening","raw_affiliation_strings":["a:1:{s:5:\"en_US\";s:6:\"Amazon\";}","a:1:{s:5:\"en_US\"","s:6:\"Amazon\""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"a:1:{s:5:\"en_US\";s:6:\"Amazon\";}","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"a:1:{s:5:\"en_US\"","institution_ids":[]},{"raw_affiliation_string":"s:6:\"Amazon\"","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.422,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.5795178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"80","issue":null,"first_page":"1099","last_page":"1137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0003000000142492354,"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":9.999999747378752e-05,"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/sparse-rewards","display_name":"sparse rewards","score":0.9070000052452087},{"id":"https://openalex.org/keywords/policy-synthesis","display_name":"policy synthesis","score":0.4320000112056732},{"id":"https://openalex.org/keywords/montezuma-s-revenge","display_name":"Montezuma's Revenge","score":0.8209999799728394},{"id":"https://openalex.org/keywords/atari-games","display_name":"Atari games","score":0.6420000195503235},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.5649999976158142}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.767850399017334},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7597411870956421},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.75080406665802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6915115714073181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6414793729782104},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5468385815620422},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44680750370025635},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17724692821502686},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08190909028053284},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06424054503440857},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1613/jair.1.14063","doi":"https://doi.org/10.1613/jair.1.14063","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.14063","pdf_url":"https://www.jair.org/index.php/jair/article/download/14063/27062","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","doaj","dongbi-b","erih-plus","jufo-3","norway-2","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:550a574d-d1c7-43c5-a30b-574f799cccb1","doi":null,"is_oa":true,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:550a574d-d1c7-43c5-a30b-574f799cccb1/files/s2n49t3694","pdf_url":"https://ora.ox.ac.uk/objects/uuid:550a574d-d1c7-43c5-a30b-574f799cccb1/files/s2n49t3694","source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"Journal article"}],"best_oa_location":{"id":"doi:10.1613/jair.1.14063","doi":"https://doi.org/10.1613/jair.1.14063","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.14063","pdf_url":"https://www.jair.org/index.php/jair/article/download/14063/27062","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","doaj","dongbi-b","erih-plus","jufo-3","norway-2","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320290","display_name":"University of Oxford","ror":"https://ror.org/052gg0110"},{"id":"https://openalex.org/F4320335172","display_name":"Balliol College, University of Oxford","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400966321.pdf","grobid_xml":"https://content.openalex.org/works/W4400966321.grobid-xml"},"referenced_works_count":92,"referenced_works":["https://openalex.org/W117707387","https://openalex.org/W166862392","https://openalex.org/W1522301498","https://openalex.org/W1529558080","https://openalex.org/W1541799124","https://openalex.org/W1559171143","https://openalex.org/W1585861384","https://openalex.org/W1669302834","https://openalex.org/W1763311249","https://openalex.org/W1989445634","https://openalex.org/W2026252407","https://openalex.org/W2062897452","https://openalex.org/W2076343783","https://openalex.org/W2078151802","https://openalex.org/W2098800875","https://openalex.org/W2103806799","https://openalex.org/W2111967991","https://openalex.org/W2136656815","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2169209873","https://openalex.org/W2170899200","https://openalex.org/W2257979135","https://openalex.org/W2321477654","https://openalex.org/W2335959470","https://openalex.org/W2408207366","https://openalex.org/W2546571074","https://openalex.org/W2553882142","https://openalex.org/W2580909119","https://openalex.org/W2588494934","https://openalex.org/W2594829461","https://openalex.org/W2605514557","https://openalex.org/W2774977638","https://openalex.org/W2783552934","https://openalex.org/W2787908307","https://openalex.org/W2789027502","https://openalex.org/W2798588334","https://openalex.org/W2808386811","https://openalex.org/W2892364860","https://openalex.org/W2902538158","https://openalex.org/W2914702425","https://openalex.org/W2953319434","https://openalex.org/W2963778636","https://openalex.org/W2963830168","https://openalex.org/W2964227312","https://openalex.org/W2966537673","https://openalex.org/W2970673985","https://openalex.org/W2972500268","https://openalex.org/W2976866784","https://openalex.org/W2982106100","https://openalex.org/W2982316857","https://openalex.org/W2989855807","https://openalex.org/W2990500698","https://openalex.org/W2996875168","https://openalex.org/W2997022832","https://openalex.org/W3000757100","https://openalex.org/W3002508808","https://openalex.org/W3006844914","https://openalex.org/W3008651843","https://openalex.org/W3011250830","https://openalex.org/W3013518705","https://openalex.org/W3018036994","https://openalex.org/W3019910725","https://openalex.org/W3037207827","https://openalex.org/W3039350634","https://openalex.org/W3045306771","https://openalex.org/W3080598349","https://openalex.org/W3088974622","https://openalex.org/W3092301589","https://openalex.org/W3119635706","https://openalex.org/W3121448578","https://openalex.org/W3130777366","https://openalex.org/W3133533407","https://openalex.org/W3173218700","https://openalex.org/W3175871729","https://openalex.org/W3195968524","https://openalex.org/W3197209873","https://openalex.org/W3208792968","https://openalex.org/W3215473757","https://openalex.org/W4214717370","https://openalex.org/W4256048145","https://openalex.org/W4295113525","https://openalex.org/W4297336624","https://openalex.org/W4307347247","https://openalex.org/W4312313389","https://openalex.org/W4320813994","https://openalex.org/W4323914099","https://openalex.org/W4387075594","https://openalex.org/W4393146535","https://openalex.org/W4408358045","https://openalex.org/W6959968929","https://openalex.org/W7133238287"],"related_works":["https://openalex.org/W7138986687","https://openalex.org/W3175871729","https://openalex.org/W7027506815","https://openalex.org/W3092213025","https://openalex.org/W7162249108","https://openalex.org/W4399850944","https://openalex.org/W2976866784","https://openalex.org/W2931553127","https://openalex.org/W4401024549","https://openalex.org/W2809801155"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"DeepSynth,":[3],"a":[4,41,59,88,129,156,171],"method":[5,39],"for":[6,44,167],"effective":[7],"training":[8],"of":[9,35,46,73,87,131,158,161],"deep":[10,92,151],"reinforcement":[11,93,152],"learning":[12,94],"agents":[13],"when":[14],"the":[15,23,28,68,74,80,85,98,103,135,164],"reward":[16,29],"is":[17,76,95,108],"sparse":[18,119],"or":[19,120],"non-Markovian,":[20],"but":[21],"at":[22],"same":[24],"time":[25],"progress":[26],"towards":[27],"requires":[30],"achieving":[31],"an":[32],"unknown":[33,118],"sequence":[34],"high-level":[36],"objectives.":[37],"Our":[38],"employs":[40],"novel":[42],"algorithm":[43],"synthesis":[45],"compact":[47],"finite":[48],"state":[49,71],"automata":[50],"to":[51,110,141,145],"uncover":[52],"this":[53],"sequential":[54],"structure":[55,100],"automatically.":[56],"We":[57,123],"synthesise":[58],"human-interpretable":[60],"automaton":[61],"from":[62],"trace":[63],"data":[64],"collected":[65],"by":[66,91,97],"exploring":[67],"environment.":[69],"The":[70,105],"space":[72],"environment":[75],"then":[77],"enriched":[78],"with":[79,112],"synthesised":[81],"automaton,":[82],"so":[83],"that":[84,133,147],"generation":[86],"control":[89],"policy":[90,168],"guided":[96],"discovered":[99],"encoded":[101],"in":[102,128,163,174],"automaton.":[104],"proposed":[106],"approach":[107],"able":[109],"cope":[111],"both":[113],"high-dimensional,":[114],"low-level":[115],"features":[116],"and":[117,170],"non-Markovian":[121],"rewards.":[122],"have":[124],"evaluated":[125],"DeepSynth\u2019s":[126],"performance":[127],"set":[130],"experiments":[132],"includes":[134],"Atari":[136],"game":[137],"Montezuma\u2019s":[138],"Revenge,":[139],"known":[140],"be":[142],"challenging.":[143],"Compared":[144],"approaches":[146],"rely":[148],"solely":[149],"on":[150],"learning,":[153],"we":[154],"obtain":[155],"reduction":[157],"two":[159],"orders":[160],"magnitude":[162],"iterations":[165],"required":[166],"synthesis,":[169],"significant":[172],"improvement":[173],"scalability.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2024-07-25T00:00:00"}