{"id":"https://openalex.org/W2962244319","doi":"https://doi.org/10.1109/devlrn.2018.8761044","title":"Deep Reinforcement Learning by Parallelizing Reward and Punishment using the MaxPain Architecture","display_name":"Deep Reinforcement Learning by Parallelizing Reward and Punishment using the MaxPain Architecture","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2962244319","doi":"https://doi.org/10.1109/devlrn.2018.8761044","mag":"2962244319"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2018.8761044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2018.8761044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","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/A5100668056","display_name":"Jiexin Wang","orcid":"https://orcid.org/0009-0004-8034-9428"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiexin Wang","raw_affiliation_strings":["Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068305732","display_name":"Stefan Elfwing","orcid":"https://orcid.org/0000-0001-6689-1000"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Stefan Elfwing","raw_affiliation_strings":["Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031054137","display_name":"Eiji Uchibe","orcid":"https://orcid.org/0000-0001-7908-0258"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eiji Uchibe","raw_affiliation_strings":["Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I4210104143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210104143"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"175","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10581","display_name":"Neural dynamics and brain function","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8976949453353882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7499698400497437},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.7019723057746887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6479083299636841},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.5626238584518433},{"id":"https://openalex.org/keywords/punishment","display_name":"Punishment (psychology)","score":0.558417558670044},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5494709014892578},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.49434852600097656},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.49187350273132324},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4498696029186249},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41137203574180603},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3903283178806305},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.16677236557006836},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.1213427484035492},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12008324265480042}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8976949453353882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7499698400497437},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.7019723057746887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6479083299636841},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.5626238584518433},{"id":"https://openalex.org/C2779295839","wikidata":"https://www.wikidata.org/wiki/Q3544090","display_name":"Punishment (psychology)","level":2,"score":0.558417558670044},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5494709014892578},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.49434852600097656},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.49187350273132324},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4498696029186249},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41137203574180603},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3903283178806305},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.16677236557006836},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.1213427484035492},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12008324265480042},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/devlrn.2018.8761044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2018.8761044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1612579644","https://openalex.org/W1828803485","https://openalex.org/W2015051472","https://openalex.org/W2083058253","https://openalex.org/W2145339207","https://openalex.org/W2338986187","https://openalex.org/W2513734981","https://openalex.org/W2561776174","https://openalex.org/W2624731731","https://openalex.org/W2795921402","https://openalex.org/W2949475445","https://openalex.org/W2950892788","https://openalex.org/W2963276097","https://openalex.org/W2963305465","https://openalex.org/W4298342547","https://openalex.org/W6717230150","https://openalex.org/W6725867758","https://openalex.org/W6730641667"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W3096874164","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3099153698","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2025663273"],"abstract_inverted_index":{"Traditionally,":[0],"reinforcement":[1,66],"learning":[2,49,53,67],"treats":[3],"punishments":[4,34],"as":[5,173],"negative":[6],"rewards.":[7],"However,":[8],"in":[9,116,122,126,174],"biological":[10],"decision":[11],"systems,":[12],"some":[13],"evidence":[14],"shows":[15],"that":[16],"animals":[17],"have":[18],"separate":[19],"systems":[20],"for":[21],"rewards":[22,32],"and":[23,33,35,41,51,107,119],"punishments.":[24,157,179],"The":[25,132],"MaxPain":[26,61,102,140,148,161],"architecture":[27,62,103],"parallelizes":[28],"the":[29,48,52,60,80,85,89,93,101,127,136,139,143,147,160,167,175],"predictions":[30],"of":[31,54,88,138,177],"scales":[36],"them":[37],"into":[38,63],"dual-attribute":[39],"policies,":[40],"has":[42],"been":[43],"shown":[44],"to":[45,73],"both":[46],"improve":[47],"speed":[50],"safer":[55],"behaviors.":[56],"This":[57],"paper":[58],"extends":[59],"a":[64,108,123],"deep":[65],"framework":[68],"using":[69],"convolutional":[70],"neural":[71],"networks":[72],"approximate":[74],"two":[75,94],"action-value":[76,95],"functions.":[77,96],"To":[78],"derive":[79],"behavioral":[81],"policy,":[82],"we":[83,99],"consider":[84],"mixture":[86],"distributions":[87],"policies":[90],"computed":[91],"from":[92],"For":[97],"evaluation,":[98],"compare":[100],"with":[104],"count-based":[105,144],"exploration":[106],"reward-decomposing":[109],"structure":[110],"called":[111],"Hybrid":[112],"Reward":[113],"Architecture":[114],"(HRA)":[115],"grid-world":[117],"navigation":[118,121],"vision-based":[120],"U-shape":[124],"maze":[125],"Gazebo":[128],"robot":[129],"simulation":[130,133],"environment.":[131],"results":[134],"show":[135],"superiority":[137],"approach":[141],"over":[142],"method":[145],"because":[146],"agents":[149,162,169],"efficiently":[150],"avoid":[151],"dead-end":[152],"states":[153],"by":[154],"predicting":[155],"future":[156],"In":[158],"addition,":[159],"learn":[163,170],"safe":[164],"behaviors,":[165,172],"while":[166],"HRA":[168],"similar":[171],"case":[176],"no":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}