{"id":"https://openalex.org/W1506480412","doi":"https://doi.org/10.1109/ccece.2015.7129295","title":"Handling stochastic reward delays in machine reinforcement learning","display_name":"Handling stochastic reward delays in machine reinforcement learning","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W1506480412","doi":"https://doi.org/10.1109/ccece.2015.7129295","mag":"1506480412"},"language":"en","primary_location":{"id":"doi:10.1109/ccece.2015.7129295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccece.2015.7129295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering (CCECE)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084154287","display_name":"J. S. Campbell","orcid":null},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jeffrey S. Campbell","raw_affiliation_strings":["Department of Systems and Computer Engineering, Carleton University, Ottawa, ON, Canada","Department of Systems and Computer Engineering, Carleton University Ottawa, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Computer Engineering, Carleton University, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I67031392"]},{"raw_affiliation_string":"Department of Systems and Computer Engineering, Carleton University Ottawa, ON, Canada","institution_ids":["https://openalex.org/I67031392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025867957","display_name":"Sidney Givigi","orcid":"https://orcid.org/0000-0002-3829-3545"},"institutions":[{"id":"https://openalex.org/I51768193","display_name":"Royal Military College of Canada","ror":"https://ror.org/04yr71909","country_code":"CA","type":"education","lineage":["https://openalex.org/I51768193"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sidney N. Givigi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Royal Military College of Canada, Kingston, ON, Canada","Department of Electrical and Computer Engineering; Royal Military College of Canada; Kingston ON Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Royal Military College of Canada, Kingston, ON, Canada","institution_ids":["https://openalex.org/I51768193"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering; Royal Military College of Canada; Kingston ON Canada","institution_ids":["https://openalex.org/I51768193"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018347314","display_name":"Howard M. Schwartz","orcid":"https://orcid.org/0000-0002-4489-5892"},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Howard M. Schwartz","raw_affiliation_strings":["Carleton University, Ottawa, ON, CA","Syst. & Comput. Eng., Carleton Univ., Ottawa, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carleton University, Ottawa, ON, CA","institution_ids":[]},{"raw_affiliation_string":"Syst. & Comput. Eng., Carleton Univ., Ottawa, ON, Canada","institution_ids":["https://openalex.org/I67031392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4115,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.55339712,"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":"314","last_page":"319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996999979019165,"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":0.996999979019165,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9930999875068665,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9047750234603882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7253325581550598},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.5579558610916138},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4848695695400238},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.46834418177604675},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4641503095626831},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.463329941034317},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.456554114818573},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4453161060810089},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.44401946663856506},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.4220414161682129},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.25242868065834045},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.24784588813781738},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14280962944030762},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13815966248512268}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9047750234603882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253325581550598},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.5579558610916138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4848695695400238},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.46834418177604675},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4641503095626831},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.463329941034317},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.456554114818573},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4453161060810089},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.44401946663856506},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.4220414161682129},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.25242868065834045},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.24784588813781738},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14280962944030762},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13815966248512268},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccece.2015.7129295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccece.2015.7129295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering (CCECE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1538318259","https://openalex.org/W1977467218","https://openalex.org/W1980722163","https://openalex.org/W1988098342","https://openalex.org/W2038651536","https://openalex.org/W2051829768","https://openalex.org/W2090434188","https://openalex.org/W2097951814","https://openalex.org/W2105422656","https://openalex.org/W2107726111","https://openalex.org/W2112382559","https://openalex.org/W2117864026","https://openalex.org/W2121863487","https://openalex.org/W2147750403","https://openalex.org/W4214717370","https://openalex.org/W4233696721","https://openalex.org/W6675591780","https://openalex.org/W6676007687"],"related_works":["https://openalex.org/W2002388147","https://openalex.org/W3098928304","https://openalex.org/W2394883510","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W2150958483","https://openalex.org/W2922503265","https://openalex.org/W2023324176","https://openalex.org/W2121097709"],"abstract_inverted_index":{"The":[0,26],"main":[1],"contribution":[2],"of":[3,38,63,81],"this":[4],"work":[5],"is":[6,50],"a":[7,55,85],"novel":[8,27],"learning":[9,14,86],"algorithm":[10],"for":[11,84],"machine":[12],"reinforcement":[13,24],"when":[15],"Poissonian":[16],"stochastic":[17,56],"time":[18,41,57],"delays":[19],"are":[20],"present":[21],"in":[22,40,88],"the":[23,61,64,73,77],"signal.":[25],"approach":[28],"can":[29],"deal":[30],"with":[31,44,52,68,91],"rewards":[32],"which":[33],"may":[34],"be":[35],"received":[36],"out":[37],"order":[39],"or":[42],"overlap":[43],"one":[45],"another.":[46],"A":[47],"PID":[48],"controller":[49],"simulated":[51],"and":[53],"without":[54],"delay":[58],"to":[59],"demonstrate":[60,71],"difficulties":[62],"problem.":[65],"Experimental":[66],"results":[67],"mobile":[69],"robots":[70],"that":[72,80],"proposed":[74],"method":[75],"improves":[76],"performance":[78],"over":[79],"traditional":[82],"Q-learning":[83],"agent":[87],"an":[89],"environment":[90],"Poissonian-type":[92],"stochastically":[93],"delayed":[94],"rewards.":[95]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}