{"id":"https://openalex.org/W4388886462","doi":"https://doi.org/10.1145/3605764.3623916","title":"Reward Shaping for Happier Autonomous Cyber Security Agents","display_name":"Reward Shaping for Happier Autonomous Cyber Security Agents","publication_year":2023,"publication_date":"2023-11-21","ids":{"openalex":"https://openalex.org/W4388886462","doi":"https://doi.org/10.1145/3605764.3623916"},"language":"en","primary_location":{"id":"doi:10.1145/3605764.3623916","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605764.3623916","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605764.3623916","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3605764.3623916","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019024267","display_name":"Elizabeth Bates","orcid":"https://orcid.org/0009-0003-5081-0052"},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Elizabeth Bates","raw_affiliation_strings":["The Alan Turing Institute, London, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0003-5081-0052","affiliations":[{"raw_affiliation_string":"The Alan Turing Institute, London, United Kingdom","institution_ids":["https://openalex.org/I4210128584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008006072","display_name":"Vasilios Mavroudis","orcid":"https://orcid.org/0000-0003-2667-5906"},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vasilios Mavroudis","raw_affiliation_strings":["The Alan Turing Institute, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-2667-5906","affiliations":[{"raw_affiliation_string":"The Alan Turing Institute, London, United Kingdom","institution_ids":["https://openalex.org/I4210128584"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080048241","display_name":"Chris Hicks","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chris Hicks","raw_affiliation_strings":["The Alan Turing Institute, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-6340-004X","affiliations":[{"raw_affiliation_string":"The Alan Turing Institute, London, United Kingdom","institution_ids":["https://openalex.org/I4210128584"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019024267"],"corresponding_institution_ids":["https://openalex.org/I4210128584"],"apc_list":null,"apc_paid":null,"fwci":2.2153,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90409335,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"221","last_page":"232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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":0.9965999722480774,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9749000072479248,"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/T11513","display_name":"stochastic dynamics and bifurcation","score":0.9138000011444092,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9070621728897095},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.8399242162704468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7728300094604492},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7174457311630249},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.6265020370483398},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5578323602676392},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5017368793487549},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4455045759677887},{"id":"https://openalex.org/keywords/compromise","display_name":"Compromise","score":0.4375540614128113},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38811761140823364},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3654487133026123},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3528493642807007},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11065268516540527},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08267107605934143}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9070621728897095},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.8399242162704468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7728300094604492},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7174457311630249},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.6265020370483398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5578323602676392},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5017368793487549},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4455045759677887},{"id":"https://openalex.org/C46355384","wikidata":"https://www.wikidata.org/wiki/Q726686","display_name":"Compromise","level":2,"score":0.4375540614128113},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38811761140823364},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3654487133026123},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3528493642807007},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11065268516540527},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08267107605934143},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605764.3623916","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605764.3623916","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605764.3623916","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3605764.3623916","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605764.3623916","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605764.3623916","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7099999785423279}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332972","display_name":"Defence Science and Technology Laboratory","ror":"https://ror.org/04jswqb94"},{"id":"https://openalex.org/F4320335334","display_name":"Defence Science and Technology Group","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388886462.pdf","grobid_xml":"https://content.openalex.org/works/W4388886462.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W1993842826","https://openalex.org/W2130750514","https://openalex.org/W2145339207","https://openalex.org/W2509960853","https://openalex.org/W2605063145","https://openalex.org/W2788455270","https://openalex.org/W2963523627","https://openalex.org/W3019200173","https://openalex.org/W3125803510","https://openalex.org/W4214717370","https://openalex.org/W4281388209","https://openalex.org/W4283800386","https://openalex.org/W4286748781","https://openalex.org/W4306999448","https://openalex.org/W4307964230","https://openalex.org/W4388837586","https://openalex.org/W4388886866"],"related_works":["https://openalex.org/W2801622120","https://openalex.org/W2164141394","https://openalex.org/W4240977217","https://openalex.org/W3036524962","https://openalex.org/W2508088450","https://openalex.org/W2389434635","https://openalex.org/W4214750239","https://openalex.org/W2279908259","https://openalex.org/W2025641871","https://openalex.org/W4252107351"],"abstract_inverted_index":{"As":[0],"machine":[1],"learning":[2,25,94,143],"models":[3],"become":[4],"more":[5,128],"capable,":[6],"they":[7],"have":[8],"exhibited":[9],"increased":[10],"potential":[11],"in":[12,30,68],"solving":[13],"complex":[14],"tasks.":[15,34,197],"One":[16],"of":[17,40,59,71,91,150],"the":[18,38,41,48,57,62,69,97,148,151],"most":[19],"promising":[20],"directions":[21],"uses":[22],"deep":[23,141],"reinforcement":[24,93,142],"to":[26,47,56,105,123,126,133,147,170],"train":[27,127],"autonomous":[28],"agents":[29,49,125],"computer":[31],"network":[32,195],"defense":[33,84],"This":[35],"work":[36],"studies":[37],"impact":[39],"reward":[42,63,87,113,182],"signal":[43,64],"that":[44,116,140],"is":[45,65,99],"provided":[46],"when":[50,74],"training":[51],"for":[52,102,109,193],"this":[53,119],"task.":[54],"Due":[55],"nature":[58],"cybersecurity":[60],"tasks,":[61],"typically":[66],"1)":[67],"form":[70],"penalties":[72,152,160],"(e.g.,":[73],"a":[75,134],"compromise":[76],"occurs),":[77],"and":[78,130,153,165,184],"2)":[79],"distributed":[80],"sparsely":[81],"across":[82],"each":[83],"episode.":[85],"Such":[86],"characteristics":[88],"are":[89,145],"atypical":[90],"classic":[92],"tasks":[95],"where":[96],"agent":[98],"regularly":[100],"rewarded":[101],"progress":[103],"(cf.":[104],"getting":[106],"occasionally":[107],"penalized":[108],"failures).":[110],"We":[111,137],"investigate":[112],"shaping":[114],"techniques":[115],"could":[117],"bridge":[118],"gap":[120],"so":[121],"as":[122,178,191],"enable":[124],"sample-efficiently":[129],"potentially":[131],"converge":[132],"better":[135],"performance.":[136],"first":[138],"show":[139],"algorithms":[144],"sensitive":[146],"magnitude":[149],"their":[154,167],"relative":[155],"size.":[156],"Then,":[157],"we":[158,174],"combine":[159],"with":[161],"positive":[162,181],"external":[163],"rewards":[164],"study":[166],"effect":[168],"compared":[169],"penalty-only":[171],"training.":[172],"Finally,":[173],"evaluate":[175],"intrinsic":[176],"curiosity":[177],"an":[179],"internal":[180],"mechanism":[183],"discuss":[185],"why":[186],"it":[187],"might":[188],"not":[189],"be":[190],"advantageous":[192],"high-level":[194],"monitoring":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}