{"id":"https://openalex.org/W3095178267","doi":"https://doi.org/10.48550/arxiv.2010.14496","title":"Generative Temporal Difference Learning for Infinite-Horizon Prediction","display_name":"Generative Temporal Difference Learning for Infinite-Horizon Prediction","publication_year":2020,"publication_date":"2020-10-27","ids":{"openalex":"https://openalex.org/W3095178267","doi":"https://doi.org/10.48550/arxiv.2010.14496","mag":"3095178267"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2010.14496","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14496","pdf_url":"https://arxiv.org/pdf/2010.14496","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.14496","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Janner, Michael","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Janner, Michael","raw_affiliation_strings":["UC Berkeley","University of California, Berkeley, Berkeley, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014193325","display_name":"Igor Mordatch","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mordatch, Igor","raw_affiliation_strings":["Google Brain","Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743","observed_orcids":["https://orcid.org/0000-0001-6764-2743"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Levine, Sergey","raw_affiliation_strings":["University of California, Berkeley, Berkeley, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1724","last_page":"1735"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.0,"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/gamma-model","display_name":"gamma model","score":0.7429999709129333},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.8320000171661377},{"id":"https://openalex.org/keywords/successor-representation","display_name":"successor representation","score":0.8130000233650208},{"id":"https://openalex.org/keywords/model-based-control","display_name":"model-based control","score":0.7879999876022339},{"id":"https://openalex.org/keywords/generative-adversarial-networks","display_name":"generative adversarial networks","score":0.8730000257492065},{"id":"https://openalex.org/keywords/normalizing-flows","display_name":"normalizing flows","score":0.9990000128746033}],"concepts":[{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.7819377183914185},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6075519323348999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5498301386833191},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5228360295295715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47816118597984314},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4584924280643463},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4566558599472046},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.45391327142715454},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44783759117126465},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.44046810269355774},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.43584030866622925},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4237244129180908},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3378114700317383},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2502453327178955},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.13516640663146973},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:arXiv.org:2010.14496","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14496","pdf_url":"https://arxiv.org/pdf/2010.14496","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3095178267","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.14496v2","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"mag:3205756646","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.14496.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2010.14496","doi":"https://doi.org/10.48550/arxiv.2010.14496","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.14496","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3098649479","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/2020/file/12ffb0968f2f56e51a59a6beb37b2859-Paper.pdf","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":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.14496","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14496","pdf_url":"https://arxiv.org/pdf/2010.14496","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320315389","display_name":"Open Philanthropy Project","ror":"https://ror.org/004d1k391"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095178267.pdf","grobid_xml":"https://content.openalex.org/works/W3095178267.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W648786980","https://openalex.org/W1491843047","https://openalex.org/W1594201624","https://openalex.org/W1594216983","https://openalex.org/W1598748993","https://openalex.org/W1600437712","https://openalex.org/W1906772730","https://openalex.org/W2043968544","https://openalex.org/W2056354534","https://openalex.org/W2072752020","https://openalex.org/W2097778153","https://openalex.org/W2099471712","https://openalex.org/W2104733512","https://openalex.org/W2109910161","https://openalex.org/W2124175081","https://openalex.org/W2145339207","https://openalex.org/W2153244676","https://openalex.org/W2154208977","https://openalex.org/W2258731934","https://openalex.org/W2404689820","https://openalex.org/W2417089653","https://openalex.org/W2419501139","https://openalex.org/W2572640103","https://openalex.org/W2593414223","https://openalex.org/W2733961795","https://openalex.org/W2735347808","https://openalex.org/W2736601468","https://openalex.org/W2743381431","https://openalex.org/W2759463506","https://openalex.org/W2774354230","https://openalex.org/W2781726626","https://openalex.org/W2787757704","https://openalex.org/W2789824229","https://openalex.org/W2797734773","https://openalex.org/W2804673281","https://openalex.org/W2805762288","https://openalex.org/W2859967432","https://openalex.org/W2883690703","https://openalex.org/W2889731659","https://openalex.org/W2947150733","https://openalex.org/W2947861305","https://openalex.org/W2950624398","https://openalex.org/W2952451928","https://openalex.org/W2953319434","https://openalex.org/W2962717849","https://openalex.org/W2962804251","https://openalex.org/W2963090522","https://openalex.org/W2963604043","https://openalex.org/W2963960193","https://openalex.org/W2964001908","https://openalex.org/W2964077562","https://openalex.org/W2964220198","https://openalex.org/W2970277495","https://openalex.org/W2970898247","https://openalex.org/W2989847975"],"related_works":["https://openalex.org/W3205756646","https://openalex.org/W3207825988","https://openalex.org/W4416033119","https://openalex.org/W2595180411","https://openalex.org/W2923023063","https://openalex.org/W7221812545","https://openalex.org/W3007220394","https://openalex.org/W2918394844","https://openalex.org/W2594533284","https://openalex.org/W7202115362"],"abstract_inverted_index":{"We":[0,89],"introduce":[1],"the":[2,25,32,56,75,91],"$\u03b3$-model,":[3,40],"a":[4,43,51,60,68,79,95],"predictive":[5,81],"model":[6,33],"of":[7,24,46,55,86],"environment":[8],"dynamics":[9],"with":[10,19,42],"an":[11,107],"infinite":[12],"probabilistic":[13],"horizon.":[14],"Replacing":[15],"standard":[16,80],"single-step":[17],"models":[18],"$\u03b3$-models":[20],"leads":[21],"to":[22,28],"generalizations":[23],"procedures":[26],"central":[27],"model-based":[29,36,65],"control,":[30],"including":[31],"rollout":[34],"and":[35,59,64,99,112,116,123],"value":[37,69],"estimation.":[38],"The":[39],"trained":[41],"generative":[44,96],"reinterpretation":[45],"temporal":[47],"difference":[48],"learning,":[49],"is":[50,84],"natural":[52],"continuous":[53],"analogue":[54],"successor":[57],"representation":[58],"hybrid":[61],"between":[62,110],"model-free":[63],"mechanisms.":[66],"Like":[67],"function,":[70],"it":[71,83],"contains":[72],"information":[73],"about":[74],"long-term":[76],"future;":[77],"like":[78],"model,":[82],"independent":[85],"task":[87],"reward.":[88],"instantiate":[90],"$\u03b3$-model":[92],"as":[93],"both":[94],"adversarial":[97],"network":[98],"normalizing":[100],"flow,":[101],"discuss":[102],"how":[103],"its":[104,119],"training":[105],"reflects":[106],"inescapable":[108],"tradeoff":[109],"training-time":[111],"testing-time":[113],"compounding":[114],"errors,":[115],"empirically":[117],"investigate":[118],"utility":[120],"for":[121],"prediction":[122],"control.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2020-11-09T00:00:00"}