{"id":"https://openalex.org/W7214031978","doi":"https://doi.org/10.48550/arxiv.2609.24025","title":"Synthesizing Reactive Character Behaviors for Continuous Games via Programmatic Policy Search","display_name":"Synthesizing Reactive Character Behaviors for Continuous Games via Programmatic Policy Search","publication_year":2026,"publication_date":"2026-09-21","ids":{"openalex":"https://openalex.org/W7214031978","doi":"https://doi.org/10.48550/arxiv.2609.24025"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.24025","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24025","pdf_url":"https://arxiv.org/pdf/2609.24025","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.24025","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094186995","display_name":"Maxim Gumin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gumin, Maxim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152482871","display_name":"Hsueh-Ti Derek Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Hsueh-Ti Derek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137147650","display_name":"Victor Zordan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zordan, Victor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005034184","display_name":"Daniel Ritchie","orcid":"https://orcid.org/0000-0002-8253-0069","observed_orcids":["https://orcid.org/0000-0002-8253-0069"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ritchie, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9897000193595886,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9897000193595886,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.00419999985024333,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.0035000001080334187,"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/program-synthesis","display_name":"program synthesis","score":0.8080000281333923},{"id":"https://openalex.org/keywords/game-ai","display_name":"game AI","score":0.671999990940094},{"id":"https://openalex.org/keywords/continuous-games","display_name":"continuous games","score":0.8700000047683716},{"id":"https://openalex.org/keywords/domain-specific-languages","display_name":"domain-specific languages","score":0.7059999704360962},{"id":"https://openalex.org/keywords/ai-coding-agents","display_name":"coding agents","score":0.8569999933242798},{"id":"https://openalex.org/keywords/behavior-trees","display_name":"behavior trees","score":0.44999998807907104},{"id":"https://openalex.org/keywords/state-machines","display_name":"state machines","score":0.40700000524520874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287999987602234},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.49129998683929443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4560999870300293},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4212000072002411},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C2776937632","wikidata":"https://www.wikidata.org/wiki/Q4117718","display_name":"Program synthesis","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C170828538","wikidata":"https://www.wikidata.org/wiki/Q1751513","display_name":"Game mechanics","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C102234262","wikidata":"https://www.wikidata.org/wiki/Q1320931","display_name":"Combinatorial game theory","level":4,"score":0.2827000021934509},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25609999895095825},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.24025","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24025","pdf_url":"https://arxiv.org/pdf/2609.24025","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.24025","doi":"https://doi.org/10.48550/arxiv.2609.24025","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.24025","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.24025","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24025","pdf_url":"https://arxiv.org/pdf/2609.24025","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214031978.pdf","grobid_xml":"https://content.openalex.org/works/W7214031978.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1524728167","https://openalex.org/W1978711911","https://openalex.org/W1987574258","https://openalex.org/W1988115241","https://openalex.org/W2056141172","https://openalex.org/W2075347672","https://openalex.org/W2101493843","https://openalex.org/W2117085697","https://openalex.org/W2137015070","https://openalex.org/W2145339207","https://openalex.org/W2150312211","https://openalex.org/W2234200704","https://openalex.org/W2313274380","https://openalex.org/W2604908377","https://openalex.org/W2736601468","https://openalex.org/W2749807327","https://openalex.org/W2792919371","https://openalex.org/W2889987506","https://openalex.org/W2913781869","https://openalex.org/W2996037775","https://openalex.org/W2997502221","https://openalex.org/W3024044737","https://openalex.org/W3145123113","https://openalex.org/W4312568367","https://openalex.org/W4395093927","https://openalex.org/W4412106517","https://openalex.org/W6891880838","https://openalex.org/W6967114952","https://openalex.org/W7133226216"],"related_works":["https://openalex.org/W4291997242","https://openalex.org/W4401024405","https://openalex.org/W7078428596","https://openalex.org/W4283791892","https://openalex.org/W7096970524","https://openalex.org/W4388834844","https://openalex.org/W7215079953","https://openalex.org/W1762378887","https://openalex.org/W4387394648","https://openalex.org/W7213259116"],"abstract_inverted_index":{"We":[0,115,149,168],"present":[1],"a":[2,58,85,100,125,154,179,199],"method":[3,152,186],"for":[4,9,61,203],"synthesizing":[5],"reactive":[6,70],"character":[7],"behaviors":[8,215],"continuous":[10,86,158],"games":[11],"as":[12,78],"compact,":[13],"human-readable":[14],"programs.":[15],"Game":[16],"AI":[17],"practice":[18],"still":[19],"relies":[20],"heavily":[21],"on":[22,153],"manually":[23],"authored":[24],"behavior":[25,87],"trees,":[26],"state":[27],"machines,":[28],"and":[29,45,73,140,210,220],"scripts,":[30],"while":[31,111,183],"academic":[32],"reinforcement":[33],"learning":[34],"typically":[35],"produces":[36],"opaque":[37],"neural":[38],"controllers":[39],"that":[40,106,170,193,216],"are":[41,217],"expensive":[42],"to":[43,47,144,165],"train":[44],"difficult":[46],"edit.":[48],"Our":[49,128,190],"approach":[50],"bridges":[51],"this":[52],"gap":[53],"by":[54],"searching":[55],"directly":[56],"over":[57],"domain-specific":[59],"language":[60,66],"continuous-space":[62],"game":[63,204],"policies.":[64],"The":[65],"is":[67,173],"designed":[68],"around":[69],"geometric":[71],"decisions":[72],"includes":[74],"higher-order":[75],"constructs":[76,82],"such":[77],"direction":[79],"maximization.":[80],"These":[81],"help":[83],"discretize":[84],"space":[88],"into":[89],"enumerable":[90],"program":[91,95,109,147],"structures.":[92],"To":[93],"make":[94],"search":[96,196],"practical,":[97],"we":[98],"introduce":[99],"large":[101],"set":[102],"of":[103,156],"synthesis":[104],"antipatterns":[105],"remove":[107],"redundant":[108],"forms":[110],"preserving":[112],"behavioral":[113],"coverage.":[114],"further":[116],"combine":[117],"bottom-up":[118],"symbolic":[119],"enumeration":[120,172],"with":[121],"top-down":[122],"guidance":[123],"from":[124,161],"coding":[126,180],"agent.":[127],"resulting":[129],"method,":[130],"agentic":[131],"sketching,":[132],"has":[133],"the":[134,151,184,211],"agent":[135,181],"propose":[136],"high-level":[137],"policy":[138,195],"structure":[139],"call":[141],"an":[142],"enumerator":[143],"complete":[145],"local":[146],"slots.":[148],"evaluate":[150],"benchmark":[155],"14":[157],"games,":[159],"ranging":[160],"classic":[162],"control":[163],"tasks":[164],"multi-agent":[166],"football.":[167],"find":[169],"pure":[171],"often":[174,221],"more":[175],"efficient":[176],"than":[177],"using":[178],"alone,":[182],"combined":[185],"substantially":[187],"outperforms":[188],"both.":[189],"results":[191],"suggest":[192],"programmatic":[194],"can":[197],"be":[198],"practical":[200],"authoring":[201],"tool":[202],"AI:":[205],"designers":[206],"specify":[207],"reward":[208],"functions,":[209],"system":[212],"discovers":[213],"editable":[214],"effective,":[218],"portable,":[219],"surprising.":[222]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-23T00:00:00"}