{"id":"https://openalex.org/W4413321737","doi":"https://doi.org/10.1109/cog64752.2025.11114393","title":"Automatic Action Space Specification for Deep Reinforcement Learning in Games via Program Analysis","display_name":"Automatic Action Space Specification for Deep Reinforcement Learning in Games via Program Analysis","publication_year":2025,"publication_date":"2025-08-19","ids":{"openalex":"https://openalex.org/W4413321737","doi":"https://doi.org/10.1109/cog64752.2025.11114393"},"language":"en","primary_location":{"id":"doi:10.1109/cog64752.2025.11114393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog64752.2025.11114393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5043362708","display_name":"Sasha Volokh","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sasha Volokh","raw_affiliation_strings":["University of Southern California,Los Angeles,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036531724","display_name":"William G. J. Halfond","orcid":"https://orcid.org/0000-0003-4951-9367"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William G.J. Halfond","raw_affiliation_strings":["University of Southern California,Los Angeles,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043362708"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12182431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9713000059127808,"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":0.9713000059127808,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7379475235939026},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7199644446372986},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6400296688079834},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.56793612241745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46163320541381836},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43035635352134705},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3655892014503479},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3574534058570862},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1456104815006256},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0833074152469635}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7379475235939026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7199644446372986},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6400296688079834},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.56793612241745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46163320541381836},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43035635352134705},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3655892014503479},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3574534058570862},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1456104815006256},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0833074152469635},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog64752.2025.11114393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog64752.2025.11114393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2097444001","https://openalex.org/W2121885527","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2763498325","https://openalex.org/W2976245088","https://openalex.org/W3000499753","https://openalex.org/W3037164854","https://openalex.org/W3094236223","https://openalex.org/W3094597259","https://openalex.org/W3136629921","https://openalex.org/W4221141793","https://openalex.org/W4284682097","https://openalex.org/W4293819875","https://openalex.org/W4296426214","https://openalex.org/W4312546215","https://openalex.org/W4387394637","https://openalex.org/W4387394771","https://openalex.org/W4389315371","https://openalex.org/W4401422722"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,62,119],"has":[2],"numerous":[3],"applications":[4],"for":[5,74],"the":[6,35,41,49,80,86,96,107,125,128,138],"testing":[7],"and":[8,31,112,141],"analysis":[9,43,129],"of":[10,28,45,82,95,102],"video":[11],"game":[12,36,50],"content.":[13],"However,":[14],"deploying":[15,60],"it":[16],"in":[17,63],"existing":[18,64],"games":[19,105],"is":[20],"a":[21,55,92,99],"challenging":[22],"engineering":[23],"effort,":[24],"requiring":[25],"suitable":[26],"representations":[27],"states,":[29],"actions,":[30],"rewards":[32],"based":[33],"on":[34,48,85,98,143],"rules.":[37],"We":[38,90],"propose":[39],"using":[40,127,133,147],"program":[42],"technique":[44,67,97],"symbolic":[46],"execution":[47],"code":[51],"to":[52],"automatically":[53,68],"determine":[54],"precise":[56],"action":[57,72,77,135,150],"model":[58],"when":[59],"reinforcement":[61,118],"games.":[65],"Our":[66],"computes":[69],"appropriate":[70],"discrete":[71],"spaces":[73,136],"games,":[75],"including":[76],"masks":[78],"indicating":[79],"validity":[81],"actions":[83],"depending":[84],"agent's":[87],"current":[88],"state.":[89],"conduct":[91],"comprehensive":[93],"evaluation":[94],"varied":[100],"dataset":[101],"seven":[103],"Unity":[104],"with":[106,145],"Proximal":[108],"Policy":[109],"Optimization":[110],"(PPO)":[111],"Deep":[113],"Q":[114],"Learning":[115],"(DQN)":[116],"deep":[117],"approaches.":[120],"The":[121],"results":[122],"show":[123],"that":[124],"agents":[126],"significantly":[130],"out-perform":[131],"those":[132,146],"generic":[134],"covering":[137],"input":[139],"device,":[140],"perform":[142],"par":[144],"manually":[148],"specified":[149],"spaces.":[151]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}