{"id":"https://openalex.org/W7034541743","doi":null,"title":"Towards Generalist Agents through Scaling Offline Reinforcement Learning","display_name":"Towards Generalist Agents through Scaling Offline Reinforcement Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W7034541743"},"language":"en","primary_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt69j3d2w2","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/69j3d2w2","pdf_url":"https://escholarship.org/content/qt69j3d2w2/qt69j3d2w2.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/content/qt69j3d2w2/qt69j3d2w2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054661138","display_name":"Edwin Zhang","orcid":"https://orcid.org/0009-0004-3984-6051","observed_orcids":["https://orcid.org/0009-0004-3984-6051","https://orcid.org/0009-0006-8091-5703"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Edwin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5054661138"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":true,"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/T12072","display_name":"Machine Learning and Algorithms","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/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.9950000047683716},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.9440000057220459},{"id":"https://openalex.org/keywords/training-instability","display_name":"training instability","score":0.8489999771118164},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.7799999713897705},{"id":"https://openalex.org/keywords/optimization-methods","display_name":"optimization methods","score":0.5659999847412109},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.5619999766349792}],"concepts":[{"id":"https://openalex.org/C45371612","wikidata":"https://www.wikidata.org/wiki/Q3058587","display_name":"Generalist and specialist species","level":3,"score":0.7551000118255615},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6834999918937683},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6700000166893005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6274999976158142},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6227999925613403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5713000297546387},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.5489000082015991},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41519999504089355},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2651999890804291},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:escholarship.org:ark:/13030/qt69j3d2w2","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/69j3d2w2","pdf_url":"https://escholarship.org/content/qt69j3d2w2/qt69j3d2w2.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"}],"best_oa_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt69j3d2w2","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/69j3d2w2","pdf_url":"https://escholarship.org/content/qt69j3d2w2/qt69j3d2w2.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7034541743.pdf","grobid_xml":"https://content.openalex.org/works/W7034541743.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W195596278","https://openalex.org/W1959608418","https://openalex.org/W2117496083","https://openalex.org/W2173248099","https://openalex.org/W2627585944","https://openalex.org/W2739490129","https://openalex.org/W2747402019","https://openalex.org/W2895560838","https://openalex.org/W2948380112","https://openalex.org/W2953981431","https://openalex.org/W2964121744","https://openalex.org/W2978455699","https://openalex.org/W2991355586","https://openalex.org/W2995264919","https://openalex.org/W3001279689","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W3034379033","https://openalex.org/W3036167779","https://openalex.org/W3036185205","https://openalex.org/W3040490156","https://openalex.org/W3092442149","https://openalex.org/W3110257065","https://openalex.org/W3170016383","https://openalex.org/W3178987284","https://openalex.org/W3190965961","https://openalex.org/W3205794883","https://openalex.org/W4221158443","https://openalex.org/W4221159132","https://openalex.org/W4221167833","https://openalex.org/W4283771519","https://openalex.org/W4285428875","https://openalex.org/W4298185919","https://openalex.org/W4303440777","https://openalex.org/W4303648971","https://openalex.org/W4307868887","https://openalex.org/W4310430604","https://openalex.org/W4383097638","https://openalex.org/W4385403811","https://openalex.org/W4385430679","https://openalex.org/W7000218544","https://openalex.org/W7133230418","https://openalex.org/W7133231380","https://openalex.org/W7133231487","https://openalex.org/W7133246205"],"related_works":["https://openalex.org/W4416168385","https://openalex.org/W3013308774","https://openalex.org/W7124260154","https://openalex.org/W7124280821","https://openalex.org/W7116427914","https://openalex.org/W7116718816","https://openalex.org/W7116414615","https://openalex.org/W4312587154","https://openalex.org/W3213132814","https://openalex.org/W7124275563"],"abstract_inverted_index":{"In":[0,48],"recent":[1],"years,":[2],"there":[3],"has":[4],"been":[5],"an":[6,26],"increasing":[7],"emphasis":[8],"on":[9],"developing":[10],"generalist":[11,59,121],"agents":[12,60],"capable":[13,30],"of":[14,19,31,58,64],"solving":[15,95],"a":[16],"diverse":[17],"variety":[18],"tasks":[20,35],"effectively.":[21],"We":[22],"hope":[23],"that":[24,113],"such":[25,81,96],"agent":[27],"would":[28],"be":[29],"chaining":[32],"several":[33,75,92],"smaller":[34],"together,":[36],"navigating":[37],"from":[38],"high-dimensional":[39],"inputs,":[40],"and":[41,44,61,69,85,102,111],"being":[42],"simple":[43],"reliable":[45],"to":[46],"train.":[47],"this":[49],"thesis,":[50],"we":[51,89,105],"will":[52,90,106],"first":[53],"introduce":[54],"the":[55,62,108,117],"current":[56],"landscape":[57],"state":[63],"Deep":[65],"Reinforcement":[66],"Learning":[67],"(RL)":[68],"Offline":[70],"RL.":[71],"We'll":[72],"also":[73],"discuss":[74,107],"major":[76,109],"issues":[77],"underlying":[78],"these":[79],"fields,":[80],"as":[82],"training":[83,120],"instability":[84],"generalization":[86],"failure.":[87],"Next,":[88],"explore":[91],"proposals":[93],"for":[94,119],"problems,":[97],"namely":[98],"through":[99],"optimization":[100],"techniques":[101],"diffusion.":[103],"Finally,":[104],"challenges":[110],"opportunities":[112],"lie":[114],"ahead":[115],"in":[116],"future":[118],"agents.":[122]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}