{"id":"https://openalex.org/W4312832139","doi":"https://doi.org/10.5220/0011326900003332","title":"Interpolated Experience Replay for Continuous Environments","display_name":"Interpolated Experience Replay for Continuous Environments","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312832139","doi":"https://doi.org/10.5220/0011326900003332"},"language":"en","primary_location":{"id":"doi:10.5220/0011326900003332","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011326900003332","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Joint Conference on Computational Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0011326900003332","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002401151","display_name":"Wenzel von Pilchau","orcid":null},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Wenzel von Pilchau","raw_affiliation_strings":["Organic Computing Group, University of Augsburg, Am Technologiezentrum 8, Augsburg, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Organic Computing Group, University of Augsburg, Am Technologiezentrum 8, Augsburg, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045271767","display_name":"Anthony Stein","orcid":"https://orcid.org/0000-0002-1808-9758"},"institutions":[{"id":"https://openalex.org/I110079840","display_name":"University of Hohenheim","ror":"https://ror.org/00b1c9541","country_code":"DE","type":"education","lineage":["https://openalex.org/I110079840"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anthony Stein","raw_affiliation_strings":["Artificial Intelligence in Agricultural Engineering, University of Hohenheim, Garbenstra\u00dfe 9, Hohenheim, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence in Agricultural Engineering, University of Hohenheim, Garbenstra\u00dfe 9, Hohenheim, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I110079840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035545860","display_name":"J\u00f6rg H\u00e4hner","orcid":"https://orcid.org/0000-0003-0107-264X"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00f6rg H\u00e4hner","raw_affiliation_strings":["Organic Computing Group, University of Augsburg, Am Technologiezentrum 8, Augsburg, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Organic Computing Group, University of Augsburg, Am Technologiezentrum 8, Augsburg, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002401151"],"corresponding_institution_ids":["https://openalex.org/I179225836"],"apc_list":null,"apc_paid":null,"fwci":0.2652,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62742179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"237","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9829999804496765,"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/computer-science","display_name":"Computer science","score":0.7910184860229492},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.7485528588294983},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7179731726646423},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6547565460205078},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.636919379234314},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49991559982299805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41563501954078674},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3865847587585449},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3574836254119873},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12860408425331116}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910184860229492},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7485528588294983},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7179731726646423},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6547565460205078},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.636919379234314},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49991559982299805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41563501954078674},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3865847587585449},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3574836254119873},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12860408425331116},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0011326900003332","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011326900003332","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Joint Conference on Computational Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:99989","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-999894","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:bookpart"}],"best_oa_location":{"id":"doi:10.5220/0011326900003332","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011326900003332","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Joint Conference on Computational Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W167680297","https://openalex.org/W1496508106","https://openalex.org/W1595483645","https://openalex.org/W2070732802","https://openalex.org/W2096698697","https://openalex.org/W2139418546","https://openalex.org/W2145339207","https://openalex.org/W2147169375","https://openalex.org/W2201581102","https://openalex.org/W2584068132","https://openalex.org/W2766447205","https://openalex.org/W2902456977","https://openalex.org/W2904246096","https://openalex.org/W2963864421","https://openalex.org/W2991594855","https://openalex.org/W2996037775","https://openalex.org/W3106070636","https://openalex.org/W3184593887","https://openalex.org/W4239187508","https://openalex.org/W4254755460","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W4289718052","https://openalex.org/W2164121020","https://openalex.org/W2145559838","https://openalex.org/W2905319430","https://openalex.org/W3116498279","https://openalex.org/W4287549553","https://openalex.org/W4310285384","https://openalex.org/W3183027292","https://openalex.org/W4248896073","https://openalex.org/W2974871044"],"abstract_inverted_index":{"The":[0,18],"concept":[1,103],"of":[2,14,31,98],"Experience":[3,84],"Replay":[4,85],"is":[5,107],"a":[6,36],"crucial":[7],"element":[8],"in":[9,47,73,111],"Deep":[10],"Reinforcement":[11],"Learning":[12],"algorithms":[13],"the":[15,29,44,48,64,74,82,120],"DQN":[16],"family.":[17],"basic":[19],"approach":[20,118],"reuses":[21],"stored":[22,89],"experiences":[23,42,58,90],"to,":[24],"amongst":[25],"other":[26],"reasons,":[27],"overcome":[28],"problem":[30,66,113],"catastrophic":[32],"forgetting":[33],"and":[34,124],"as":[35],"result":[37],"stabilize":[38],"learning.":[39],"However,":[40],"only":[41],"that":[43,56,67,87],"learner":[45],"observed":[46],"past":[49],"are":[50],"used":[51],"for":[52,104],"updates.":[53],"We":[54,115],"anticipate":[55],"these":[57],"posses":[59],"additional":[60],"valuable":[61],"information":[62],"about":[63],"underlying":[65],"just":[68],"needs":[69],"to":[70,91,109],"be":[71],"extracted":[72],"right":[75],"way.":[76],"To":[77],"achieve":[78],"this,":[79],"we":[80],"present":[81],"Interpolated":[83],"technique":[86],"leverages":[88],"create":[92],"new,":[93],"synthetic":[94],"ones":[95],"by":[96],"means":[97],"interpolation.":[99],"A":[100],"previous":[101],"proposed":[102],"discrete-state":[105],"environments":[106],"extended":[108],"work":[110],"continuous":[112],"spaces.":[114],"evaluate":[116],"our":[117],"on":[119],"MountainCar":[121],"benchmark":[122],"environment":[123],"demonstrate":[125],"its":[126],"promising":[127],"potential.":[128]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}