{"id":"https://openalex.org/W4385768192","doi":"https://doi.org/10.24963/ijcai.2023/601","title":"Generalization through Diversity: Improving Unsupervised Environment Design","display_name":"Generalization through Diversity: Improving Unsupervised Environment Design","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385768192","doi":"https://doi.org/10.24963/ijcai.2023/601"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/601","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/601","pdf_url":"https://www.ijcai.org/proceedings/2023/0601.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0601.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100446243","display_name":"Wenjun Li","orcid":"https://orcid.org/0000-0001-5042-7756"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenjun Li","raw_affiliation_strings":["Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089113099","display_name":"Pradeep Varakantham","orcid":"https://orcid.org/0000-0001-7342-5745"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Pradeep Varakantham","raw_affiliation_strings":["Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035910198","display_name":"Dexun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dexun Li","raw_affiliation_strings":["Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5089113099"],"corresponding_institution_ids":["https://openalex.org/I79891267"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5411","last_page":"5419"},"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11182","display_name":"Auction Theory and Applications","score":0.986299991607666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8255953788757324},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7784039378166199},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6341110467910767},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5986882448196411},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5626689195632935},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5411028861999512},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5338692665100098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8255953788757324},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7784039378166199},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6341110467910767},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5986882448196411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5626689195632935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5411028861999512},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5338692665100098},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/601","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/601","pdf_url":"https://www.ijcai.org/proceedings/2023/0601.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/601","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/601","pdf_url":"https://www.ijcai.org/proceedings/2023/0601.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3642752407","display_name":null,"funder_award_id":"AISG2-RP-2020-017","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385768192.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1977023370","https://openalex.org/W2105078254","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2464736835","https://openalex.org/W2605102758","https://openalex.org/W2736601468","https://openalex.org/W2787800669","https://openalex.org/W2809668646","https://openalex.org/W2903181768","https://openalex.org/W2908460759","https://openalex.org/W2962957005","https://openalex.org/W2963684914","https://openalex.org/W2964848402","https://openalex.org/W2981030070","https://openalex.org/W2981234930","https://openalex.org/W2994073215","https://openalex.org/W3004082694","https://openalex.org/W3032597593","https://openalex.org/W3101966195","https://openalex.org/W3110161557","https://openalex.org/W3129170303","https://openalex.org/W3171752851","https://openalex.org/W3172688350","https://openalex.org/W3197608410","https://openalex.org/W3213432714","https://openalex.org/W4226197112","https://openalex.org/W4287018575","https://openalex.org/W4287245321","https://openalex.org/W4288374418","https://openalex.org/W4297789758","https://openalex.org/W6675860490","https://openalex.org/W6791858558","https://openalex.org/W6864014924"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Agent":[0],"decision":[1],"making":[2,140],"using":[3,107],"Reinforcement":[4],"Learning":[5],"(RL)":[6],"heavily":[7],"relies":[8],"on":[9,29,75,86,144,165,194],"either":[10],"a":[11,127,134,156,166],"model":[12],"or":[13],"simulator":[14],"of":[15,44,50,58,79,148,181],"the":[16,40,47,51,56,59,63,96,99,113,118,123,177],"environment":[17,41,105,172,192],"(e.g.,":[18,42],"moving":[19],"in":[20,39,46,103,184,200],"an":[21,30,76,104],"8x8":[22,31],"maze":[23],"with":[24],"three":[25,195],"rooms,":[26],"playing":[27],"Chess":[28],"board).":[32],"Due":[33],"to":[34,83,101,116,121,137,159,171,186],"this":[35],"dependence,":[36],"small":[37],"changes":[38],"positions":[43],"obstacles":[45],"maze,":[48],"size":[49],"board)":[52],"can":[53,129],"severely":[54],"affect":[55],"effectiveness":[57,180],"policy":[60],"learned":[61],"by":[62],"agent.":[64,124],"To":[65,151],"that":[66,152],"end,":[67,153],"existing":[68,92],"work":[69],"has":[70,94],"proposed":[71],"training":[72,142],"RL":[73],"agents":[74],"adaptive":[77],"curriculum":[78],"environments":[80,132,163],"(generated":[81],"automatically)":[82],"improve":[84],"performance":[85],"out-of-distribution":[87],"(OOD)":[88],"test":[89],"scenarios.":[90],"Specifically,":[91],"research":[93],"employed":[95],"potential":[97,136],"for":[98,190],"agent":[100,141],"learn":[102],"(captured":[106],"Generalized":[108],"Advantage":[109],"Estimation,":[110],"GAE)":[111],"as":[112],"key":[114],"factor":[115],"select":[117,130],"next":[119],"environment(s)":[120],"train":[122],"However,":[125],"such":[126],"mechanism":[128],"similar":[131],"(with":[133],"high":[135],"learn)":[138],"thereby":[139],"redundant":[143],"all":[145],"but":[146],"one":[147],"those":[149],"environments.":[150],"we":[154],"provide":[155],"principled":[157],"approach":[158],"adaptively":[160],"identify":[161],"diverse":[162],"based":[164],"novel":[167],"distance":[168],"measure":[169],"relevant":[170],"design.":[173],"We":[174],"empirically":[175],"demonstrate":[176],"versatility":[178],"and":[179],"our":[182],"method":[183],"comparison":[185],"multiple":[187],"leading":[188],"approaches":[189],"unsupervised":[191],"design":[193],"distinct":[196],"benchmark":[197],"problems":[198],"used":[199],"literature.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}