{"id":"https://openalex.org/W3013308774","doi":null,"title":"On Building Generalizable Learning Agents","display_name":"On Building Generalizable Learning Agents","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W3013308774","mag":"3013308774"},"language":"en","primary_location":{"id":"pmh:oai:escholarship.org/ark:/13030/qt2595c945","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/2595c945","pdf_url":"https://escholarship.org/uc/item/2595c945","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/uc/item/2595c945","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025990925","display_name":"Yi Wu","orcid":"https://orcid.org/0000-0001-5704-2111","observed_orcids":["https://orcid.org/0000-0001-5704-2111"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yi Wu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5704-2111","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5025990925"],"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":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0020000000949949026,"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/generalization","display_name":"generalization","score":0.8370000123977661},{"id":"https://openalex.org/keywords/learning-agents","display_name":"learning agents","score":0.7860000133514404},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8859999775886536},{"id":"https://openalex.org/keywords/visual-navigation","display_name":"visual navigation","score":0.800000011920929},{"id":"https://openalex.org/keywords/3d-navigation","display_name":"3D navigation","score":0.8519999980926514},{"id":"https://openalex.org/keywords/multi-agent-games","display_name":"multi-agent games","score":0.9850000143051147},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"natural language processing","score":0.8360000252723694}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7642772197723389},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7576479911804199},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7484052777290344},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5586535930633545},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5572575926780701},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5522843599319458},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5135543346405029},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4958568513393402},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4840187728404999},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07917490601539612},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:escholarship.org/ark:/13030/qt2595c945","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/2595c945","pdf_url":"https://escholarship.org/uc/item/2595c945","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"},{"id":"pmh:oai:berkeley.edu:28722-bk0018d8x1h","doi":null,"is_oa":false,"landing_page_url":"http://techreports.lib.berkeley.edu/reports/TRWebData/accessPages/EECS-2020-9.html","pdf_url":null,"source":{"id":"https://openalex.org/S7407050879","display_name":"UC Berkeley","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I95457486","host_organization_name":"University of California, Berkeley","host_organization_lineage":["https://openalex.org/I95457486"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"technical reports"},{"id":"mag:3013308774","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/content/qt2595c945/qt2595c945.pdf?t=q6z2ii","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:escholarship.org/ark:/13030/qt2595c945","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/2595c945","pdf_url":"https://escholarship.org/uc/item/2595c945","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3013308774.pdf","grobid_xml":"https://content.openalex.org/works/W3013308774.grobid-xml"},"referenced_works_count":239,"referenced_works":["https://openalex.org/W27961112","https://openalex.org/W114565888","https://openalex.org/W174427690","https://openalex.org/W199719331","https://openalex.org/W322312141","https://openalex.org/W613766092","https://openalex.org/W769612788","https://openalex.org/W1488766761","https://openalex.org/W1507852408","https://openalex.org/W1513468570","https://openalex.org/W1514535095","https://openalex.org/W1542941925","https://openalex.org/W1560074431","https://openalex.org/W1579853615","https://openalex.org/W1604644367","https://openalex.org/W1641379095","https://openalex.org/W1764574858","https://openalex.org/W1771410628","https://openalex.org/W1779483307","https://openalex.org/W1824523713","https://openalex.org/W1903029394","https://openalex.org/W1906772730","https://openalex.org/W1931877416","https://openalex.org/W1952506714","https://openalex.org/W1959608418","https://openalex.org/W1960579544","https://openalex.org/W1963576113","https://openalex.org/W1982696459","https://openalex.org/W1993979041","https://openalex.org/W2013614847","https://openalex.org/W2022508996","https://openalex.org/W2029143333","https://openalex.org/W2048500237","https://openalex.org/W2070797946","https://openalex.org/W2077069816","https://openalex.org/W2084920657","https://openalex.org/W2094728533","https://openalex.org/W2095705004","https://openalex.org/W2096145798","https://openalex.org/W2096354165","https://openalex.org/W2097381042","https://openalex.org/W2097498347","https://openalex.org/W2098161266","https://openalex.org/W2098694378","https://openalex.org/W2099471712","https://openalex.org/W2099618002","https://openalex.org/W2105078254","https://openalex.org/W2106837051","https://openalex.org/W2107544712","https://openalex.org/W2107598941","https://openalex.org/W2107726111","https://openalex.org/W2108598243","https://openalex.org/W2108892923","https://openalex.org/W2109910161","https://openalex.org/W2116442740","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2122398932","https://openalex.org/W2123491406","https://openalex.org/W2124654932","https://openalex.org/W2128554449","https://openalex.org/W2128643385","https://openalex.org/W2132679783","https://openalex.org/W2132708887","https://openalex.org/W2135194391","https://openalex.org/W2136445846","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2145680191","https://openalex.org/W2146502635","https://openalex.org/W2146881125","https://openalex.org/W2149698362","https://openalex.org/W2150468603","https://openalex.org/W2155027007","https://openalex.org/W2155454737","https://openalex.org/W2158057652","https://openalex.org/W2160371091","https://openalex.org/W2162021827","https://openalex.org/W2165150801","https://openalex.org/W2165698076","https://openalex.org/W2168342951","https://openalex.org/W2172933221","https://openalex.org/W2173248099","https://openalex.org/W2176412452","https://openalex.org/W2186389117","https://openalex.org/W2194321275","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2250880399","https://openalex.org/W2251135946","https://openalex.org/W2251622960","https://openalex.org/W2257979135","https://openalex.org/W2258731934","https://openalex.org/W2260756217","https://openalex.org/W2296673577","https://openalex.org/W2335959470","https://openalex.org/W2336416123","https://openalex.org/W2341171179","https://openalex.org/W2362143032","https://openalex.org/W2384495648","https://openalex.org/W2395575420","https://openalex.org/W2396783599","https://openalex.org/W2400532028","https://openalex.org/W2402144811","https://openalex.org/W2415755012","https://openalex.org/W2417988721","https://openalex.org/W2427497464","https://openalex.org/W2441569124","https://openalex.org/W2460657278","https://openalex.org/W2478027467","https://openalex.org/W2487770199","https://openalex.org/W2504108613","https://openalex.org/W2511964075","https://openalex.org/W2515462165","https://openalex.org/W2525778437","https://openalex.org/W2528489519","https://openalex.org/W2528501250","https://openalex.org/W2530944449","https://openalex.org/W2534269850","https://openalex.org/W2545316382","https://openalex.org/W2547416798","https://openalex.org/W2547875792","https://openalex.org/W2551887912","https://openalex.org/W2553882142","https://openalex.org/W2557465155","https://openalex.org/W2558535589","https://openalex.org/W2558634851","https://openalex.org/W2559767995","https://openalex.org/W2561715562","https://openalex.org/W2567015638","https://openalex.org/W2577666659","https://openalex.org/W2591644541","https://openalex.org/W2591844545","https://openalex.org/W2592798481","https://openalex.org/W2593649546","https://openalex.org/W2593841437","https://openalex.org/W2594103415","https://openalex.org/W2594903727","https://openalex.org/W2594978815","https://openalex.org/W2602963933","https://openalex.org/W2603266952","https://openalex.org/W2604283518","https://openalex.org/W2605102758","https://openalex.org/W2611884151","https://openalex.org/W2615146352","https://openalex.org/W2620290674","https://openalex.org/W2624780181","https://openalex.org/W2627585944","https://openalex.org/W2674709473","https://openalex.org/W2739083961","https://openalex.org/W2740839465","https://openalex.org/W2741548518","https://openalex.org/W2745990901","https://openalex.org/W2749807327","https://openalex.org/W2760600531","https://openalex.org/W2762872434","https://openalex.org/W2767050701","https://openalex.org/W2768629321","https://openalex.org/W2770387316","https://openalex.org/W2772390515","https://openalex.org/W2773691349","https://openalex.org/W2774005037","https://openalex.org/W2774661387","https://openalex.org/W2776202271","https://openalex.org/W2777629900","https://openalex.org/W2780351918","https://openalex.org/W2786122328","https://openalex.org/W2786478526","https://openalex.org/W2786487443","https://openalex.org/W2787270134","https://openalex.org/W2787501667","https://openalex.org/W2788781499","https://openalex.org/W2795911278","https://openalex.org/W2798511001","https://openalex.org/W2799269579","https://openalex.org/W2883471708","https://openalex.org/W2884565639","https://openalex.org/W2890010095","https://openalex.org/W2895453875","https://openalex.org/W2895915466","https://openalex.org/W2899138465","https://openalex.org/W2901725278","https://openalex.org/W2902729397","https://openalex.org/W2902907165","https://openalex.org/W2904455790","https://openalex.org/W2907502844","https://openalex.org/W2908633661","https://openalex.org/W2913340405","https://openalex.org/W2918642789","https://openalex.org/W2919115771","https://openalex.org/W2945924974","https://openalex.org/W2950472486","https://openalex.org/W2950999850","https://openalex.org/W2951896791","https://openalex.org/W2952125132","https://openalex.org/W2960876848","https://openalex.org/W2962789679","https://openalex.org/W2962793481","https://openalex.org/W2962812366","https://openalex.org/W2962867954","https://openalex.org/W2962887844","https://openalex.org/W2962938168","https://openalex.org/W2962941327","https://openalex.org/W2963088756","https://openalex.org/W2963150697","https://openalex.org/W2963207607","https://openalex.org/W2963230247","https://openalex.org/W2963245725","https://openalex.org/W2963341956","https://openalex.org/W2963346996","https://openalex.org/W2963398599","https://openalex.org/W2963407617","https://openalex.org/W2963430173","https://openalex.org/W2963486920","https://openalex.org/W2963577640","https://openalex.org/W2963627051","https://openalex.org/W2963647251","https://openalex.org/W2963726321","https://openalex.org/W2963881016","https://openalex.org/W2963937357","https://openalex.org/W2964084698","https://openalex.org/W2964094751","https://openalex.org/W2964121744","https://openalex.org/W2964153729","https://openalex.org/W2964161785","https://openalex.org/W2964164804","https://openalex.org/W2964191473","https://openalex.org/W2964199361","https://openalex.org/W2964338167","https://openalex.org/W2964339842","https://openalex.org/W2964345382","https://openalex.org/W2970971581","https://openalex.org/W2981030070","https://openalex.org/W2982316857","https://openalex.org/W2983335573","https://openalex.org/W2989847975","https://openalex.org/W2996037775","https://openalex.org/W6922505924","https://openalex.org/W6998967213"],"related_works":["https://openalex.org/W7034541743","https://openalex.org/W1537116105","https://openalex.org/W3185826690","https://openalex.org/W2889989545","https://openalex.org/W7124260154","https://openalex.org/W3106363827","https://openalex.org/W6959626846","https://openalex.org/W3029947299","https://openalex.org/W1489072559","https://openalex.org/W7124275563"],"abstract_inverted_index":{"It":[0],"has":[1],"been":[2,43],"a":[3,56,129,137,210,249],"long-standing":[4],"goal":[5],"in":[6,26,46,115,128,144,209,217,248],"Artificial":[7],"Intelligence":[8],"(AI)":[9],"to":[10,21,32,51,88,120,157,182,243],"build":[11],"machines":[12],"that":[13,17,82,91,236],"can":[14,86,240],"solve":[15,33,55],"tasks":[16,34,230],"humans":[18],"can.":[19],"Thanks":[20],"the":[22,83,100,112,122,141,145,159,169,195,237],"recent":[23],"rapid":[24],"progress":[25],"data-driven":[27,79],"methods,":[28],"which":[29],"train":[30],"agents":[31,85,127],"by":[35,135,175],"learning":[36,49,126,149],"from":[37,180],"massive":[38],"training":[39,162],"data,":[40],"there":[41],"have":[42],"many":[44],"successes":[45,80],"applying":[47],"such":[48],"approaches":[50],"handle":[52],"and":[53,69,117,150,184,204,215,223],"even":[54],"number":[57],"of":[58,125,131,140,147,161,171,252],"extremely":[59],"challenging":[60],"tasks,":[61],"including":[62],"image":[63],"classification,":[64],"language":[65,228],"generation,":[66],"robotics":[67],"control,":[68],"several":[70],"multi-player":[71],"games.":[72],"The":[73],"key":[74],"factor":[75],"for":[76,102,164],"all":[77],"these":[78,189],"is":[81,99],"trained":[84],"generalize":[87],"test":[89],"scenarios":[90],"are":[92],"unseen":[93],"during":[94],"training.":[95],"This":[96,108],"generalization":[97,123,142,246],"capability":[98],"foundation":[101],"building":[103],"any":[104],"practical":[105],"AI":[106],"system.":[107],"thesis":[109],"studies":[110],"generalization,":[111],"fundamental":[113],"challenge":[114],"AI,":[116],"proposes":[118],"solutions":[119],"improve":[121],"performances":[124,247],"variety":[130],"problems.":[132,253],"We":[133,167],"start":[134],"providing":[136],"formal":[138],"formulation":[139,156],"problem":[143],"context":[146],"reinforcement":[148],"proposing":[151],"4":[152,177],"principles":[153,174,239],"within":[154],"this":[155],"guide":[158],"design":[160],"techniques":[163,187],"improved":[165,245],"generalization.":[166],"validate":[168],"effectiveness":[170],"our":[172],"proposed":[173,238],"considering":[176],"different":[178],"domains,":[179],"simple":[181],"complex,":[183],"developing":[185],"domain-specific":[186],"following":[188],"principles.":[190],"Particularly,":[191],"we":[192],"begin":[193],"with":[194],"simplest":[196],"domain,":[197],"i.e.,":[198],"path-finding":[199],"on":[200],"graphs":[201],"(Part":[202,213,221,231],"I),":[203],"then":[205],"consider":[206],"visual":[207],"navigation":[208],"3D":[211],"world":[212],"II)":[214],"competition":[216],"complex":[218],"multi-agent":[219],"games":[220],"III),":[222],"lastly":[224],"tackle":[225],"some":[226],"natural":[227],"processing":[229],"IV).":[232],"Empirical":[233],"evidences":[234],"demonstrate":[235],"generally":[241],"lead":[242],"much":[244],"wide":[250],"range":[251]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-04-03T00:00:00"}