{"id":"https://openalex.org/W4296474750","doi":"https://doi.org/10.1109/cog51982.2022.9893546","title":"Mitigating Cowardice for Reinforcement Learning Agents in Combat Scenarios","display_name":"Mitigating Cowardice for Reinforcement Learning Agents in Combat Scenarios","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4296474750","doi":"https://doi.org/10.1109/cog51982.2022.9893546"},"language":"en","primary_location":{"id":"doi:10.1109/cog51982.2022.9893546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},"type":"article","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/A5077168553","display_name":"Steve Bakos","orcid":"https://orcid.org/0000-0002-4984-0970"},"institutions":[{"id":"https://openalex.org/I39470171","display_name":"University of Ontario Institute of Technology","ror":"https://ror.org/016zre027","country_code":"CA","type":"education","lineage":["https://openalex.org/I39470171"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Steve Bakos","raw_affiliation_strings":["Ontario Tech University,Oshawa,Canada","Ontario Tech University, Oshawa, Canada"],"affiliations":[{"raw_affiliation_string":"Ontario Tech University,Oshawa,Canada","institution_ids":["https://openalex.org/I39470171"]},{"raw_affiliation_string":"Ontario Tech University, Oshawa, Canada","institution_ids":["https://openalex.org/I39470171"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014081539","display_name":"Heidar Davoudi","orcid":"https://orcid.org/0000-0002-9603-9625"},"institutions":[{"id":"https://openalex.org/I39470171","display_name":"University of Ontario Institute of Technology","ror":"https://ror.org/016zre027","country_code":"CA","type":"education","lineage":["https://openalex.org/I39470171"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Heidar Davoudi","raw_affiliation_strings":["Ontario Tech University,Oshawa,Canada","Ontario Tech University, Oshawa, Canada"],"affiliations":[{"raw_affiliation_string":"Ontario Tech University,Oshawa,Canada","institution_ids":["https://openalex.org/I39470171"]},{"raw_affiliation_string":"Ontario Tech University, Oshawa, Canada","institution_ids":["https://openalex.org/I39470171"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077168553"],"corresponding_institution_ids":["https://openalex.org/I39470171"],"apc_list":null,"apc_paid":null,"fwci":0.2776,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63208595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"377","last_page":"384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.913100004196167,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.911300003528595,"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/cowardice","display_name":"Cowardice","score":0.8853470683097839},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7497221231460571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5980139374732971},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5424872040748596},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.36425089836120605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3476426601409912},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2563881278038025},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07654273509979248}],"concepts":[{"id":"https://openalex.org/C2779640164","wikidata":"https://www.wikidata.org/wiki/Q1401607","display_name":"Cowardice","level":2,"score":0.8853470683097839},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7497221231460571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5980139374732971},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5424872040748596},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.36425089836120605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3476426601409912},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2563881278038025},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07654273509979248},{"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog51982.2022.9893546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1589774673","https://openalex.org/W2145339207","https://openalex.org/W2563112808","https://openalex.org/W2736601468","https://openalex.org/W2935192495","https://openalex.org/W2963890729","https://openalex.org/W2996037775","https://openalex.org/W3094607870","https://openalex.org/W4298857966","https://openalex.org/W4302969537","https://openalex.org/W6637967152","https://openalex.org/W6741002519","https://openalex.org/W6750022948","https://openalex.org/W6750348766","https://openalex.org/W6761513822","https://openalex.org/W6772005887","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4381511388","https://openalex.org/W4254747453","https://openalex.org/W4392332975","https://openalex.org/W2498548052","https://openalex.org/W2071471047","https://openalex.org/W2808648603","https://openalex.org/W4206121412","https://openalex.org/W3119662295","https://openalex.org/W3045160754","https://openalex.org/W2460836326"],"abstract_inverted_index":{"A":[0],"common":[1],"approach":[2,27,85],"in":[3,35,51],"reinforcement":[4],"learning":[5],"(RL)":[6],"is":[7,137],"to":[8,29,33,64,86,138,146],"give":[9],"the":[10,18,53,65,68,98,102,107,135,140,151],"agent":[11,66],"a":[12,30,40,83],"static":[13,61],"reward":[14,75,93,155],"for":[15,23],"successfully":[16],"completing":[17],"task":[19],"or":[20,94],"punishing":[21],"it":[22],"failing.":[24],"However,":[25],"this":[26,72,92],"leads":[28],"behaviour":[31],"similar":[32],"fear":[34],"combat":[36,132],"scenarios.":[37],"It":[38],"learns":[39],"sub-optimal":[41],"policy":[42],"improving":[43],"over":[44],"time":[45],"while":[46],"retaining":[47],"elements":[48],"of":[49,74,114,117,120],"cowardice":[50],"updating":[52],"policy.":[54],"Cowardice":[55],"can":[56,76],"be":[57],"avoided":[58],"by":[59,90,142],"removing":[60],"rewards":[62],"given":[63],"at":[67,101],"terminal":[69,103],"state,":[70],"but":[71],"lack":[73],"negatively":[77],"affect":[78],"performance.":[79],"This":[80],"paper":[81],"presents":[82],"novel":[84],"solve":[87],"these":[88],"issues":[89],"decaying":[91],"punishment":[95,157],"based":[96,130],"on":[97,131],"agent\u2019s":[99],"performance":[100],"state":[104],"and":[105,124,156,167],"evaluates":[106],"proposed":[108],"method":[109],"across":[110],"three":[111,127],"separate":[112],"games":[113,128],"varying":[115],"levels":[116],"complexity\u2014The":[118],"Legend":[119],"Zelda,":[121],"Megaman":[122],"X,":[123],"M.U.G.E.N.":[125],"All":[126],"are":[129,158],"scenarios":[133],"where":[134],"goal":[136],"defeat":[139],"opponent":[141],"reducing":[143],"its":[144],"health":[145],"zero.":[147],"In":[148],"all":[149],"environments,":[150],"agents":[152],"receiving":[153],"decayed":[154],"more":[159],"stable":[160],"when":[161],"training,":[162],"achieve":[163],"higher":[164],"win":[165],"rates,":[166],"require":[168],"fewer":[169],"actions":[170],"per":[171],"game":[172],"than":[173],"their":[174],"statically":[175],"rewarded":[176],"counterparts.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-22T08:38:42.863108","created_date":"2025-10-10T00:00:00"}