{"id":"https://openalex.org/W2964141050","doi":"https://doi.org/10.24963/ijcai.2018/426","title":"Learning to Design Games: Strategic Environments in Reinforcement Learning","display_name":"Learning to Design Games: Strategic Environments in Reinforcement Learning","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2964141050","doi":"https://doi.org/10.24963/ijcai.2018/426","mag":"2964141050"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/426","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/426","pdf_url":"https://www.ijcai.org/proceedings/2018/0426.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0426.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100399680","display_name":"Haifeng Zhang","orcid":"https://orcid.org/0000-0002-9890-8345"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Zhang","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384727","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-4021-4228"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100599390","display_name":"Zhiming Zhou","orcid":"https://orcid.org/0000-0002-7028-7866"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiming Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090720315","display_name":"Weinan Zhang","orcid":"https://orcid.org/0000-0002-0127-2425"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weinan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108710982","display_name":"Yin Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yin Wen","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001571390","display_name":"Yong Yu","orcid":"https://orcid.org/0000-0003-0281-8271"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Yu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100397214","display_name":"Wenxin Li","orcid":"https://orcid.org/0000-0003-1744-7792"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Li","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3516,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86509347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3068","last_page":"3074"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9751999974250793,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9750000238418579,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9253516793251038},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7268495559692383},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7153418660163879},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5661373138427734},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.49697640538215637},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.462312787771225},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.43682074546813965},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4232887625694275},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4230005741119385},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42235666513442993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41461390256881714},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36687058210372925},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28346148133277893},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11282745003700256},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11094772815704346},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09093332290649414}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9253516793251038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7268495559692383},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7153418660163879},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5661373138427734},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.49697640538215637},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.462312787771225},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.43682074546813965},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4232887625694275},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4230005741119385},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42235666513442993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41461390256881714},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36687058210372925},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28346148133277893},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11282745003700256},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11094772815704346},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09093332290649414},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2018/426","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/426","pdf_url":"https://www.ijcai.org/proceedings/2018/0426.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/426","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/426","pdf_url":"https://www.ijcai.org/proceedings/2018/0426.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G129499350","display_name":"\u7f51\u7edc\u5e7f\u544a\u62cd\u5356\u7684\u535a\u5f08\u7406\u8bba\u548c\u8ba1\u7b97\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61632017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964141050.pdf","grobid_xml":"https://content.openalex.org/works/W2964141050.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W57172406","https://openalex.org/W1491843047","https://openalex.org/W1515851193","https://openalex.org/W1542941925","https://openalex.org/W1757796397","https://openalex.org/W1845972764","https://openalex.org/W1986459634","https://openalex.org/W2012634103","https://openalex.org/W2048226872","https://openalex.org/W2099618002","https://openalex.org/W2105078254","https://openalex.org/W2107726111","https://openalex.org/W2119717200","https://openalex.org/W2120846115","https://openalex.org/W2124657875","https://openalex.org/W2144230296","https://openalex.org/W2145339207","https://openalex.org/W2149551746","https://openalex.org/W2155027007","https://openalex.org/W2163602945","https://openalex.org/W2168115594","https://openalex.org/W2257979135","https://openalex.org/W2949267040","https://openalex.org/W3105140685","https://openalex.org/W3213976271","https://openalex.org/W4214717370","https://openalex.org/W4245108548","https://openalex.org/W4298857966","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2379651310"],"abstract_inverted_index":{"In":[0,33],"typical":[1],"reinforcement":[2],"learning":[3,15],"(RL),":[4],"the":[5,11,14,23,31,42,55,58,70,92,97,107,130,133],"environment":[6,43,66,93],"is":[7,16,44,63],"assumed":[8],"given":[9],"and":[10,49,78,99,139],"goal":[12],"of":[13,132],"to":[17,94,105],"identify":[18],"an":[19],"optimal":[20],"policy":[21,102],"for":[22],"agent":[24,56,144],"taking":[25],"actions":[26],"through":[27,51],"its":[28,52],"interactions":[29],"with":[30,54],"environment.":[32,109],"this":[34,38],"paper,":[35],"we":[36,83],"extend":[37],"setting":[39],"by":[40,65,115],"considering":[41],"not":[45],"given,":[46],"but":[47],"controllable":[48],"learnable":[50],"interaction":[53],"at":[57],"same":[59],"time.":[60],"This":[61],"extension":[62],"motivated":[64],"design":[67,77,127],"scenarios":[68],"in":[69,136],"real-world,":[71],"including":[72],"game":[73,126],"design,":[74],"shopping":[75],"space":[76],"traffic":[79],"signal":[80],"design.":[81],"Theoretically,":[82],"find":[84],"a":[85,101,116,124],"dual":[86],"Markov":[87],"decision":[88],"process":[89],"(MDP)":[90],"w.r.t.":[91,96],"that":[95],"agent,":[98],"derive":[100],"gradient":[103],"solution":[104],"optimizing":[106],"parametrized":[108],"Furthermore,":[110],"discontinuous":[111],"environments":[112],"are":[113],"addressed":[114],"proposed":[117,134],"general":[118],"generative":[119],"framework.":[120],"Our":[121],"experiments":[122],"on":[123],"Maze":[125],"task":[128],"show":[129],"effectiveness":[131],"algorithms":[135],"generating":[137],"diverse":[138],"challenging":[140],"Mazes":[141],"against":[142],"various":[143],"settings.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}