{"id":"https://openalex.org/W4389364307","doi":"https://doi.org/10.48550/arxiv.2312.01939","title":"Foundations for Transfer in Reinforcement Learning: A Taxonomy of Knowledge Modalities","display_name":"Foundations for Transfer in Reinforcement Learning: A Taxonomy of Knowledge Modalities","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4389364307","doi":"https://doi.org/10.48550/arxiv.2312.01939"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2312.01939","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.01939","pdf_url":"https://arxiv.org/pdf/2312.01939","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":null},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.01939","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002747297","display_name":"Markus Wulfmeier","orcid":"https://orcid.org/0000-0003-1802-4492"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wulfmeier, Markus","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037305533","display_name":"Arunkumar Byravan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Byravan, Arunkumar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090921029","display_name":"Sarah Bechtle","orcid":"https://orcid.org/0000-0002-1705-3147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bechtle, Sarah","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088777896","display_name":"Karol Hausman","orcid":"https://orcid.org/0000-0002-1504-6197"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hausman, Karol","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5062951341","display_name":"Nicolas Heess","orcid":"https://orcid.org/0000-0001-7876-9256"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heess, Nicolas","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002747297"],"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":0.9787999987602234,"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":0.9787999987602234,"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/T10260","display_name":"Software Engineering Research","score":0.9207000136375427,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.690920889377594},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6672725677490234},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6668758988380432},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.5907467007637024},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.46975448727607727},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4610326588153839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45311933755874634},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.4400199055671692},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.4190386235713959},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.41430747509002686},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16896027326583862},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.1296980381011963},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08471429347991943}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.690920889377594},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6672725677490234},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6668758988380432},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.5907467007637024},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46975448727607727},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4610326588153839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45311933755874634},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.4400199055671692},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.4190386235713959},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.41430747509002686},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16896027326583862},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.1296980381011963},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08471429347991943},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2312.01939","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.01939","pdf_url":"https://arxiv.org/pdf/2312.01939","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":null},{"id":"doi:10.48550/arxiv.2312.01939","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.01939","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.01939","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.01939","pdf_url":"https://arxiv.org/pdf/2312.01939","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W2011264131","https://openalex.org/W4306904969","https://openalex.org/W4306353150","https://openalex.org/W2026860389","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W8219677","https://openalex.org/W3216879894","https://openalex.org/W2890132085"],"abstract_inverted_index":{"Contemporary":[0],"artificial":[1],"intelligence":[2],"systems":[3],"exhibit":[4],"rapidly":[5],"growing":[6],"abilities":[7],"accompanied":[8],"by":[9],"the":[10,57,64,80,86,103,165,174,183],"growth":[11],"of":[12,51,61,82,88,157,169,172,185],"required":[13],"resources,":[14],"expansive":[15],"datasets":[16],"and":[17,36,53,59,69,96,102,112,121,126,151,181],"corresponding":[18],"investments":[19],"into":[20],"computing":[21],"infrastructure.":[22],"Although":[23],"earlier":[24],"successes":[25],"predominantly":[26],"focus":[27],"on":[28,117],"constrained":[29],"settings,":[30],"recent":[31],"strides":[32],"in":[33,55],"fundamental":[34],"research":[35],"applications":[37],"aspire":[38],"to":[39,134,164,189],"create":[40],"increasingly":[41],"general":[42],"systems.":[43],"This":[44,106],"evolving":[45],"landscape":[46],"presents":[47],"a":[48,72],"dual":[49],"panorama":[50],"opportunities":[52],"challenges":[54],"refining":[56],"generalisation":[58,153],"transfer":[60],"knowledge":[62,89],"-":[63],"extraction":[65],"from":[66,187],"existing":[67],"sources":[68],"adaptation":[70],"as":[71,144],"comprehensive":[73],"foundation":[74],"for":[75,128],"tackling":[76],"new":[77],"problems.":[78],"Within":[79],"domain":[81],"reinforcement":[83],"learning":[84],"(RL),":[85],"representation":[87],"manifests":[90],"through":[91],"various":[92],"modalities,":[93],"including":[94],"dynamics":[95],"reward":[97],"models,":[98],"value":[99],"functions,":[100],"policies,":[101],"original":[104],"data.":[105],"taxonomy":[107],"systematically":[108],"targets":[109],"these":[110,179],"modalities":[111],"frames":[113],"its":[114],"discussion":[115],"based":[116],"their":[118],"inherent":[119,175],"properties":[120],"alignment":[122],"with":[123],"different":[124],"objectives":[125],"mechanisms":[127],"transfer.":[129,191],"Where":[130],"possible,":[131],"we":[132,160],"aim":[133],"provide":[135],"coarse":[136],"guidance":[137],"delineating":[138],"approaches":[139],"which":[140],"address":[141],"requirements":[142],"such":[143],"limiting":[145],"environment":[146],"interactions,":[147],"maximising":[148],"computational":[149],"efficiency,":[150],"enhancing":[152],"across":[154],"varying":[155],"axes":[156],"change.":[158],"Finally,":[159],"analyse":[161],"reasons":[162],"contributing":[163],"prevalence":[166],"or":[167],"scarcity":[168],"specific":[170],"forms":[171],"transfer,":[173],"potential":[176],"behind":[177],"pushing":[178],"frontiers,":[180],"underscore":[182],"significance":[184],"transitioning":[186],"designed":[188],"learned":[190]},"counts_by_year":[],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}