{"id":"https://openalex.org/W3112108956","doi":"https://doi.org/10.1109/cog52621.2021.9619084","title":"Demonstration-Efficient Inverse Reinforcement Learning in Procedurally Generated Environments","display_name":"Demonstration-Efficient Inverse Reinforcement Learning in Procedurally Generated Environments","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W3112108956","doi":"https://doi.org/10.1109/cog52621.2021.9619084","mag":"3112108956"},"language":"en","primary_location":{"id":"doi:10.1109/cog52621.2021.9619084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9619084","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5087665560","display_name":"Alessandro Sestini","orcid":null},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alessandro Sestini","raw_affiliation_strings":["Dipartimento di Ingegneria dell'Informazione, Universit\u00e0 degli Studi di Firenze, Florence, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria dell'Informazione, Universit\u00e0 degli Studi di Firenze, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040529511","display_name":"Alexander Kuhnle","orcid":"https://orcid.org/0000-0002-2361-115X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexander Kuhnle","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064029620","display_name":"Andrew D. Bagdanov","orcid":"https://orcid.org/0000-0001-6408-7043"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrew D. Bagdanov","raw_affiliation_strings":["Dipartimento di Ingegneria dell'Informazione, Universit\u00e0 degli Studi di Firenze, Florence, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria dell'Informazione, Universit\u00e0 degli Studi di Firenze, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087665560"],"corresponding_institution_ids":["https://openalex.org/I45084792"],"apc_list":null,"apc_paid":null,"fwci":0.5026,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.63684801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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":0.9994000196456909,"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":0.9994000196456909,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9939000010490417,"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/T10028","display_name":"Topic Modeling","score":0.9900000095367432,"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":0.8290035724639893},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7843877673149109},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7101892232894897},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7035564184188843},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6889102458953857},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6295751333236694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6150194406509399},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.54608553647995},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5315902829170227},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4988570213317871},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4172343909740448},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.299713134765625},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09195971488952637}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8290035724639893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7843877673149109},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7101892232894897},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7035564184188843},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6889102458953857},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6295751333236694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6150194406509399},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.54608553647995},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5315902829170227},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4988570213317871},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4172343909740448},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.299713134765625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09195971488952637},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cog52621.2021.9619084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9619084","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},{"id":"pmh:oai:flore.unifi.it:2158/1261562","is_oa":false,"landing_page_url":"http://hdl.handle.net/2158/1261562","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1931877416","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2099471712","https://openalex.org/W2113023245","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155007355","https://openalex.org/W2156869222","https://openalex.org/W2158782408","https://openalex.org/W2174803659","https://openalex.org/W2290104316","https://openalex.org/W2462906003","https://openalex.org/W2566467060","https://openalex.org/W2736601468","https://openalex.org/W2891790128","https://openalex.org/W2898191412","https://openalex.org/W2920684403","https://openalex.org/W2962943921","https://openalex.org/W2962957031","https://openalex.org/W2963041308","https://openalex.org/W2963277051","https://openalex.org/W2963508354","https://openalex.org/W2963590100","https://openalex.org/W2963684088","https://openalex.org/W2964161785","https://openalex.org/W2964263543","https://openalex.org/W2964836580","https://openalex.org/W2966556569","https://openalex.org/W2969452868","https://openalex.org/W2972245108","https://openalex.org/W2982316857","https://openalex.org/W2989656431","https://openalex.org/W2993763638","https://openalex.org/W2994073215","https://openalex.org/W2994972935","https://openalex.org/W2996037775","https://openalex.org/W3035076526","https://openalex.org/W3037871539","https://openalex.org/W3047290399","https://openalex.org/W3103780890","https://openalex.org/W3169208910","https://openalex.org/W4288347236","https://openalex.org/W4289288058","https://openalex.org/W4320013936","https://openalex.org/W4321392130","https://openalex.org/W6638018090","https://openalex.org/W6640174482","https://openalex.org/W6674884181","https://openalex.org/W6676728370","https://openalex.org/W6682849425","https://openalex.org/W6685352114","https://openalex.org/W6685664872","https://openalex.org/W6696380822","https://openalex.org/W6718092244","https://openalex.org/W6718836005","https://openalex.org/W6731259203","https://openalex.org/W6739585900","https://openalex.org/W6741002519","https://openalex.org/W6753960536","https://openalex.org/W6754521519","https://openalex.org/W6755724153","https://openalex.org/W6766549211","https://openalex.org/W6767235572","https://openalex.org/W6768425981","https://openalex.org/W6770218150","https://openalex.org/W6771750343"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W4376166922","https://openalex.org/W2490526372","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1,57,111],"Learning":[2,58,112],"achieves":[3],"very":[4],"good":[5,69,100],"results":[6,70],"in":[7,27,122],"domains":[8],"where":[9],"reward":[10,63,101,158],"functions":[11,64,159],"can":[12,60,114],"be":[13],"manually":[14],"engineered.":[15],"At":[16],"the":[17,25,92,117,126,163,169],"same":[18],"time,":[19],"there":[20,76],"is":[21,44,88,151],"growing":[22],"interest":[23],"within":[24],"community":[26],"using":[28],"games":[29],"based":[30,107],"on":[31,72,108,174],"Procedurally":[32],"Content":[33],"Generation":[34],"(PCG)":[35],"as":[36],"benchmark":[37],"environments":[38],"since":[39],"this":[40],"type":[41],"of":[42,51,80,94,128,135,171,184],"environment":[43,130],"perfect":[45],"for":[46,119,181],"studying":[47],"overfitting":[48],"and":[49,153,179],"generalization":[50],"agents":[52],"under":[53],"domain":[54],"shift.":[55],"Inverse":[56,110],"(IRL)":[59],"instead":[61],"extrapolate":[62,157],"from":[65],"expert":[66,120],"demonstrations,":[67],"with":[68,131],"even":[71],"high-dimensional":[73],"problems,":[74],"however":[75],"are":[77],"no":[78],"examples":[79],"applying":[81],"these":[82],"techniques":[83],"to":[84,91,97,142,156,162],"procedurally-generated":[85],"environments.":[86],"This":[87],"mostly":[89],"due":[90],"number":[93],"demonstrations":[95,121],"needed":[96],"find":[98],"a":[99,105,132,182],"model.":[102],"We":[103,167],"propose":[104],"technique":[106,173],"Adversarial":[109],"which":[113,160],"significantly":[115],"decrease":[116],"need":[118],"PCG":[123],"games.":[124],"Through":[125],"use":[127],"an":[129],"limited":[133],"set":[134],"initial":[136],"seed":[137],"levels,":[138],"plus":[139],"some":[140],"modifications":[141],"stabilize":[143],"training,":[144],"we":[145],"show":[146],"that":[147],"our":[148,172],"approach,":[149],"DE-AIRL,":[150],"demonstration-efficient":[152],"still":[154],"able":[155],"generalize":[161],"fully":[164],"procedural":[165,176],"domain.":[166],"demonstrate":[168],"effectiveness":[170],"two":[175],"environments,":[177],"MiniGrid":[178],"DeepCrawl,":[180],"variety":[183],"tasks.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-12-21T00:00:00"}