{"id":"https://openalex.org/W3131612349","doi":null,"title":"Data-Efficient Reinforcement and Transfer Learning in Robotics","display_name":"Data-Efficient Reinforcement and Transfer Learning in Robotics","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3131612349","mag":"3131612349"},"language":"en","primary_location":{"id":"pmh:oai:DiVA.org:kth-285993","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-285993","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/doctoralThesis"},"parent_works":[],"lineage":["https://openalex.org/W3131612349"],"child_works_count":0,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-285993","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100329946","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0002-3680-7485","observed_orcids":["https://orcid.org/0000-0002-3680-7485","https://orcid.org/0000-0003-4221-4288","https://orcid.org/0000-0002-3577-3308","https://orcid.org/0000-0002-3135-4114","https://orcid.org/0000-0001-5686-6741"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xi Chen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4221-4288","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100329946"],"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":0.00019999999494757503,"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/T10653","display_name":"Robot Manipulation and Learning","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"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8050000071525574},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.8709999918937683},{"id":"https://openalex.org/keywords/meta-learning","display_name":"meta-learning","score":0.9679999947547913},{"id":"https://openalex.org/keywords/data-efficient-learning","display_name":"data-efficient learning","score":0.8080000281333923},{"id":"https://openalex.org/keywords/robotics","display_name":"robotics","score":0.6759999990463257},{"id":"https://openalex.org/keywords/few-shot-adaptation","display_name":"few-shot adaptation","score":0.6779999732971191},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.7239999771118164},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.7940000295639038},{"id":"https://openalex.org/keywords/motion-control","display_name":"motion control","score":0.8420000076293945},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.8539999723434448},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.4259999990463257},{"id":"https://openalex.org/keywords/skill-acquisition","display_name":"skill acquisition","score":0.39399999380111694}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6857388019561768},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.580845057964325},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5290711522102356},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5272561311721802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4865495264530182},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38748663663864136},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.23111361265182495}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:DiVA.org:kth-285993","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-285993","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/doctoralThesis"},{"id":"mag:3131612349","doi":null,"is_oa":false,"landing_page_url":"http://kth.diva-portal.org/smash/record.jsf?pid=diva2:1501390","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:DiVA.org:kth-285993","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-285993","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/doctoralThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2954970763","https://openalex.org/W4281630699","https://openalex.org/W7070636510","https://openalex.org/W6945374213","https://openalex.org/W7196959258","https://openalex.org/W4285077530","https://openalex.org/W7098171008","https://openalex.org/W4413881917","https://openalex.org/W4402545715","https://openalex.org/W2999490157"],"abstract_inverted_index":{"In":[0,80,158],"the":[1,88,103,113,136,141,146,159,164,175,178,183,186,191,198,208,211,248,262,265,270],"past":[2,94],"few":[3,253],"years,":[4],"deep":[5],"reinforcement":[6],"learning":[7,14,63,98,106,110,127,169],"(RL)":[8],"has":[9],"shown":[10],"great":[11],"potential":[12],"in":[13,25,90,144,251],"action":[15],"selection":[16],"policies":[17],"for":[18,72,229],"solving":[19,145],"different":[20],"tasks.Despite":[21],"its":[22],"impressive":[23],"success":[24],"games,":[26],"several":[27],"challenges":[28,89],"remain,":[29],"such":[30,189],"as":[31,166,217],"designing":[32],"appropriate":[33],"reward":[34],"functions,":[35],"collecting":[36],"large":[37],"amounts":[38],"of":[39,61,105,109,205,236,247,264,275],"interactive":[40],"data,":[41,188,304],"and":[42,64,119,139,171,185,221,277,286,307],"dealing":[43],"with":[44,299],"unseen":[45],"cases,":[46],"which":[47,116],"make":[48],"it":[49,216],"difficult":[50],"to":[51,55,67,76,86,101,152,173,197,296],"apply":[52],"RL":[53,74,91],"algorithms":[54,85],"real-world":[56,78],"robotics":[57],"tasks.":[58,157],"The":[59],"ability":[60],"data-efficient":[62],"rapid":[65,230],"adaptation":[66,231],"novel":[68],"cases":[69],"is":[70,117,226],"essential":[71],"an":[73],"agent":[75],"solve":[77],"problems.":[79],"this":[81],"thesis,":[82],"we":[83,124,162,214,241],"discuss":[84],"address":[87],"by":[92,268],"reusing":[93],"experiences":[95],"gained":[96],"while":[97],"other":[99],"tasks":[100,130,298],"improve":[102],"efficiency":[104],"new":[107,258],"tasks.Instead":[108],"directly":[111],"from":[112,128,207],"target":[114,137,147,187,199,209],"task,":[115],"complicated":[118],"sometimes":[120],"unavailable":[121],"during":[122],"training,":[123],"propose":[125],"first":[126,160],"relevant":[129],"that":[131,190,225],"contain":[132],"valuable":[133],"information":[134],"about":[135],"environment,":[138],"reuse":[140],"obtained":[142],"solutions":[143],"task.We":[148],"follow":[149],"two":[150],"approaches":[151],"achieve":[153],"knowledge":[154],"sharing":[155],"between":[156,177],"approach,":[161,213],"model":[163,224,250],"problem":[165,170,220],"a":[167,202,218,223,233,252,257,273],"transfer":[168],"learn":[172,243],"minimize":[174],"distance":[176],"representations":[179],"found":[180],"based":[181],"on":[182,245,272],"training":[184],"learned":[192],"solution":[193],"can":[194,242,293],"be":[195,294],"applied":[196,295],"task":[200],"using":[201,232],"small":[203,234],"amount":[204,235],"data":[206],"environment.In":[210],"second":[212],"formulate":[215],"meta-learning":[219],"obtain":[222],"explicitly":[227],"trained":[228,249],"data.":[237],"At":[238],"test":[239],"time,":[240],"quickly":[244],"top":[246],"iterations":[254],"when":[255],"facing":[256],"task.":[259],"We":[260,288],"demonstrate":[261],"effectiveness":[263],"proposed":[266],"frameworks":[267],"evaluating":[269],"methods":[271,292],"number":[274],"real":[276],"simulated":[278],"robotic":[279],"tasks,":[280],"including":[281],"robot":[282],"navigation,":[283],"motion":[284],"control,":[285],"manipulation.":[287],"show":[289],"how":[290],"these":[291],"challenging":[297],"high-dimensional":[300],"state/action":[301],"spaces,":[302],"limited":[303],"sparse":[305],"rewards,":[306],"requiring":[308],"diverse":[309],"skills.":[310]},"counts_by_year":[],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2021-03-01T00:00:00"}