{"id":"https://openalex.org/W3035595221","doi":null,"title":"The Impact of Non-stationarity on Generalisation in Deep Reinforcement Learning","display_name":"The Impact of Non-stationarity on Generalisation in Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-06-10","ids":{"openalex":"https://openalex.org/W3035595221","mag":"3035595221"},"language":"en","primary_location":{"id":"mag:3035595221","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.05826","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.05826","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024136382","display_name":"Maximilian Igl","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maximilian Igl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016496356","display_name":"Gregory Farquhar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gregory Farquhar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020311328","display_name":"Jelena Luketina","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jelena Luketina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033832179","display_name":"Wendelin B\u00f6hmer","orcid":"https://orcid.org/0000-0002-4398-6792","observed_orcids":["https://orcid.org/0000-0002-4398-6792"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wendelin Boehmer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056879203","display_name":"Shimon Whiteson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shimon Whiteson","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":14,"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/T11574","display_name":"Artificial Intelligence in Games","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/nonstationarity","display_name":"non-stationarity","score":0.9900000095367432},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.8669999837875366},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.996999979019165},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"knowledge transfer","score":0.6769999861717224},{"id":"https://openalex.org/keywords/function-approximation","display_name":"function approximation","score":0.5450000166893005},{"id":"https://openalex.org/keywords/behavior-policy","display_name":"behavioral public policy","score":0.5109999775886536},{"id":"https://openalex.org/keywords/procgen","display_name":"Procgen","score":0.7680000066757202}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8441257476806641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6757967472076416},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.670285701751709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6226556301116943},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5910572409629822},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48707273602485657},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4432266652584076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1738179624080658},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3035595221","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.05826","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3035595221","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.05826","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1931877416","https://openalex.org/W2060277733","https://openalex.org/W2100677568","https://openalex.org/W2115524942","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2156371714","https://openalex.org/W2168342951","https://openalex.org/W2169136412","https://openalex.org/W2174786457","https://openalex.org/W2194775991","https://openalex.org/W2605102758","https://openalex.org/W2624780181","https://openalex.org/W2743151379","https://openalex.org/W2768578623","https://openalex.org/W2786036274","https://openalex.org/W2788388592","https://openalex.org/W2803740478","https://openalex.org/W2899402383","https://openalex.org/W2903158431","https://openalex.org/W2903181768","https://openalex.org/W2963199420","https://openalex.org/W2964222566","https://openalex.org/W2970176896","https://openalex.org/W2970214542","https://openalex.org/W2996309822","https://openalex.org/W2999617596","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W3118409705","https://openalex.org/W7124330495","https://openalex.org/W2949464762","https://openalex.org/W2916826721","https://openalex.org/W7124317355","https://openalex.org/W2127530277","https://openalex.org/W4327486977","https://openalex.org/W3213132814","https://openalex.org/W4416252423","https://openalex.org/W7005531169"],"abstract_inverted_index":{"Non-stationarity":[0],"arises":[1],"in":[2,7,26,51,58],"Reinforcement":[3],"Learning":[4],"(RL)":[5],"even":[6,30],"stationary":[8],"environments.":[9],"Most":[10],"RL":[11,27,82,92],"algorithms":[12],"collect":[13],"new":[14],"data":[15],"throughout":[16],"training,":[17],"using":[18,70],"a":[19,32,103],"non-stationary":[20],"behaviour":[21],"policy.":[22],"Furthermore,":[23],"training":[24,93],"targets":[25],"can":[28,63],"change":[29],"with":[31],"fixed":[33],"state":[34],"distribution":[35],"when":[36,69],"the":[37,99,122],"policy,":[38],"critic,":[39],"or":[40],"bootstrap":[41],"values":[42],"are":[43],"updated.":[44],"We":[45],"study":[46],"these":[47],"types":[48],"of":[49,80,98],"non-stationarity":[50,111],"supervised":[52],"learning":[53],"settings":[54],"as":[55,57],"well":[56],"RL,":[59],"finding":[60],"that":[61,117],"they":[62],"lead":[64],"to":[65,77],"worse":[66],"generalisation":[67,79,124],"performance":[68,120],"deep":[71,81],"neural":[72],"network":[73],"function":[74],"approximators.":[75],"Consequently,":[76],"improve":[78],"agents,":[83],"we":[84,115],"propose":[85],"Iterated":[86],"Relearning":[87],"(ITER).":[88],"ITER":[89,118],"augments":[90],"standard":[91],"by":[94],"repeated":[95],"knowledge":[96],"transfer":[97],"current":[100],"policy":[101],"into":[102],"freshly":[104],"initialised":[105],"network,":[106],"which":[107],"thereby":[108],"experiences":[109],"less":[110],"during":[112],"training.":[113],"Experimentally,":[114],"show":[116],"improves":[119],"on":[121],"challenging":[123],"benchmarks":[125],"ProcGen":[126],"and":[127],"Multiroom.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2020-06-19T00:00:00"}