{"id":"https://openalex.org/W7133246740","doi":"https://doi.org/10.52202/075280-3408","title":"Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets","display_name":"Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W7133246740","doi":"https://doi.org/10.52202/075280-3408"},"language":"en","primary_location":{"id":"doi:10.52202/075280-3408","doi":"https://doi.org/10.52202/075280-3408","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-3408","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.14069","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068752520","display_name":"Anirudhan Badrinath","orcid":"https://orcid.org/0000-0003-4572-4566","observed_orcids":["https://orcid.org/0000-0003-4572-4566"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anirudhan Badrinath","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045192384","display_name":"Yannis Flet-Berliac","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yannis Flet-Berliac","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018535992","display_name":"Allen Nie","orcid":"https://orcid.org/0000-0001-6483-2111","observed_orcids":["https://orcid.org/0000-0001-6483-2111"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Allen Nie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084989076","display_name":"Emma Brunskill","orcid":"https://orcid.org/0000-0002-3971-7127","observed_orcids":["https://orcid.org/0000-0002-3971-7127"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emma Brunskill","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9942,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80603975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"78006","last_page":"78027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/decision-transformer","display_name":"decision transformer","score":0.847000002861023},{"id":"https://openalex.org/keywords/intermediate-targets","display_name":"intermediate targets","score":0.9539999961853027},{"id":"https://openalex.org/keywords/trajectory-segmentation","display_name":"trajectory segmentation","score":0.6159999966621399},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.8019999861717224},{"id":"https://openalex.org/keywords/kitchen-environment","display_name":"kitchen environment","score":0.6800000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6396999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118999719619751},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4602999985218048},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4205000102519989},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.24230000376701355},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.24210000038146973}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/075280-3408","doi":"https://doi.org/10.52202/075280-3408","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-3408","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2306.14069","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.14069","pdf_url":"https://arxiv.org/pdf/2306.14069","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2306.14069","doi":"https://doi.org/10.48550/arxiv.2306.14069","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2306.14069","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.14069","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.14069","pdf_url":"https://arxiv.org/pdf/2306.14069","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6186404519","display_name":"RI: Small: Using and Gathering Data for Efficient Batch Reinforcement Learning","funder_award_id":"2112926","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133246740.pdf","grobid_xml":"https://content.openalex.org/works/W7133246740.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2992155277","https://openalex.org/W2993446282","https://openalex.org/W2997876358","https://openalex.org/W3016525976","https://openalex.org/W3034767611","https://openalex.org/W3048825312","https://openalex.org/W3205794883","https://openalex.org/W3216752036","https://openalex.org/W4223423875","https://openalex.org/W4226395791","https://openalex.org/W4285604474","https://openalex.org/W4295356277","https://openalex.org/W4378713420","https://openalex.org/W7133184108","https://openalex.org/W7133196022","https://openalex.org/W7133211669"],"related_works":["https://openalex.org/W4391549745","https://openalex.org/W7124287323","https://openalex.org/W4405778674","https://openalex.org/W4226395791","https://openalex.org/W4313443363","https://openalex.org/W7135890873","https://openalex.org/W3212637808","https://openalex.org/W4387390368","https://openalex.org/W4403573965","https://openalex.org/W4399310716"],"abstract_inverted_index":{"Despite":[0],"the":[1,13,16,68,78,93,115,123],"recent":[2],"advancements":[3],"in":[4,21,28,39,92,122],"offline":[5],"reinforcement":[6],"learning":[7,10],"via":[8],"supervised":[9],"(RvS)":[11],"and":[12,81,117,127,134],"success":[14],"of":[15,35,46],"decision":[17],"transformer":[18],"(DT)":[19],"architecture":[20,74],"various":[22],"domains,":[23],"DTs":[24],"have":[25],"fallen":[26],"short":[27],"several":[29],"challenging":[30,125],"benchmarks.":[31],"The":[32,86],"root":[33],"cause":[34],"this":[36,51],"underperformance":[37],"lies":[38],"their":[40],"inability":[41],"to":[42,58,97],"seamlessly":[43],"connect":[44],"segments":[45],"suboptimal":[47],"trajectories.":[48],"To":[49],"overcome":[50],"limitation,":[52],"we":[53],"present":[54],"a":[55,89],"novel":[56],"approach":[57],"enhance":[59],"RvS":[60,99],"methods":[61],"by":[62],"integrating":[63],"intermediate":[64],"targets.":[65],"We":[66],"introduce":[67],"Waypoint":[69],"Transformer":[70],"(WT),":[71],"using":[72],"an":[73],"that":[75],"builds":[76],"upon":[77],"DT":[79],"framework":[80],"conditioned":[82],"on":[83,103],"automatically-generated":[84],"waypoints.":[85],"results":[87],"show":[88],"significant":[90],"increase":[91],"final":[94],"return":[95],"compared":[96],"existing":[98,108],"methods,":[100],"with":[101],"performance":[102,116],"par":[104],"or":[105],"greater":[106],"than":[107],"state-of-the-art":[109],"temporal":[110],"difference":[111],"learning-based":[112],"methods.":[113],"Additionally,":[114],"stability":[118],"improvements":[119],"are":[120],"largest":[121],"most":[124],"environments":[126],"data":[128],"configurations,":[129],"including":[130],"AntMaze":[131],"Large":[132],"Play/Diverse":[133],"Kitchen":[135],"Mixed/Partial.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-03-03T00:00:00"}