{"id":"https://openalex.org/W3035337758","doi":"https://doi.org/10.48550/arxiv.2006.09234","title":"Model Embedding Model-Based Reinforcement Learning","display_name":"Model Embedding Model-Based Reinforcement Learning","publication_year":2020,"publication_date":"2020-06-16","ids":{"openalex":"https://openalex.org/W3035337758","doi":"https://doi.org/10.48550/arxiv.2006.09234","mag":"3035337758"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2006.09234","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.09234","pdf_url":"https://arxiv.org/pdf/2006.09234","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.09234","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102869238","display_name":"Xiaoyu Tan","orcid":"https://orcid.org/0000-0003-3555-7143","observed_orcids":["https://orcid.org/0000-0003-3555-7143"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Qu, Chao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu, Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112414661","display_name":"Junwu Xiong","orcid":"https://orcid.org/0009-0008-8508-9011","observed_orcids":["https://orcid.org/0009-0008-8508-9011"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Junwu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101545814","display_name":"James Zhang","orcid":"https://orcid.org/0000-0002-1867-7875","observed_orcids":["https://orcid.org/0000-0002-1867-7875","https://orcid.org/0000-0001-6519-676X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, James","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.9950000047683716},{"id":"https://openalex.org/keywords/model-embedding","display_name":"model embedding","score":0.8460000157356262},{"id":"https://openalex.org/keywords/model-bias","display_name":"model bias","score":0.7049999833106995},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.9670000076293945},{"id":"https://openalex.org/keywords/probabilistic-reinforcement-learning","display_name":"probabilistic reinforcement learning","score":0.8330000042915344},{"id":"https://openalex.org/keywords/value-function-learning","display_name":"value function learning","score":0.8180000185966492},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.9470000267028809},{"id":"https://openalex.org/keywords/policy-update","display_name":"policy update","score":0.6970000267028809}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8035451769828796},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6694998741149902},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5661640167236328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5057015419006348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.412385493516922},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22002100944519043},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08078494668006897}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2006.09234","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.09234","pdf_url":"https://arxiv.org/pdf/2006.09234","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":"doi:10.48550/arxiv.2006.09234","doi":"https://doi.org/10.48550/arxiv.2006.09234","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.09234","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.09234","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.09234","pdf_url":"https://arxiv.org/pdf/2006.09234","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W385466589","https://openalex.org/W1491843047","https://openalex.org/W1570233100","https://openalex.org/W1771410628","https://openalex.org/W1906772730","https://openalex.org/W2087617385","https://openalex.org/W2098774185","https://openalex.org/W2104733512","https://openalex.org/W2121103318","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2290104316","https://openalex.org/W2594103415","https://openalex.org/W2743381431","https://openalex.org/W2774354230","https://openalex.org/W2781726626","https://openalex.org/W2785389871","https://openalex.org/W2787938642","https://openalex.org/W2799151646","https://openalex.org/W2859967432","https://openalex.org/W2892230114","https://openalex.org/W2949608212","https://openalex.org/W2950564923","https://openalex.org/W2953708620","https://openalex.org/W2962879692","https://openalex.org/W2963267001","https://openalex.org/W2963960193","https://openalex.org/W2970277495"],"related_works":["https://openalex.org/W4392693740","https://openalex.org/W2966961840","https://openalex.org/W3017367030","https://openalex.org/W4360764683","https://openalex.org/W4391259941","https://openalex.org/W2953708620","https://openalex.org/W3155729845","https://openalex.org/W3011422492","https://openalex.org/W4205752284","https://openalex.org/W3106764401"],"abstract_inverted_index":{"Model-based":[0],"reinforcement":[1,12,46,56],"learning":[2,13,47],"(MBRL)":[3],"has":[4],"shown":[5],"its":[6],"advantages":[7],"in":[8,50,72,81],"sample-efficiency":[9,61],"over":[10],"model-free":[11],"(MFRL).":[14],"Despite":[15],"the":[16,27,51,54,60,73,79,82,92,98,104,109],"impressive":[17],"results":[18],"it":[19,21],"achieves,":[20],"still":[22],"faces":[23],"a":[24,40],"trade-off":[25],"between":[26],"ease":[28],"of":[29,53,101],"data":[30,71,94],"generation":[31],"and":[32,42,62,69,85,88,111,121],"model":[33,63,80,110],"bias.":[34],"In":[35,75],"this":[36],"paper,":[37],"we":[38,65,77,115],"propose":[39],"simple":[41],"elegant":[43],"model-embedding":[44],"model-based":[45],"(MEMB)":[48],"algorithm":[49,124],"framework":[52],"probabilistic":[55],"learning.":[57],"To":[58],"balance":[59],"bias,":[64],"exploit":[66],"both":[67],"real":[68,93],"imaginary":[70],"training.":[74],"particular,":[76],"embed":[78],"policy":[83],"update":[84],"learn":[86],"$Q$":[87],"$V$":[89],"functions":[90],"from":[91],"set.":[95],"We":[96],"provide":[97],"theoretical":[99],"analysis":[100],"MEMB":[102,117],"with":[103],"Lipschitz":[105],"continuity":[106],"assumption":[107],"on":[108,118],"policy.":[112],"At":[113],"last,":[114],"evaluate":[116],"several":[119],"benchmarks":[120],"demonstrate":[122],"our":[123],"can":[125],"achieve":[126],"state-of-the-art":[127],"performance.":[128]},"counts_by_year":[],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2020-06-19T00:00:00"}