{"id":"https://openalex.org/W4327521011","doi":"https://doi.org/10.1145/3573428.3573729","title":"Deep reinforcement learning and imitation learning based on VizDoom","display_name":"Deep reinforcement learning and imitation learning based on VizDoom","publication_year":2022,"publication_date":"2022-10-21","ids":{"openalex":"https://openalex.org/W4327521011","doi":"https://doi.org/10.1145/3573428.3573729"},"language":"en","primary_location":{"id":"doi:10.1145/3573428.3573729","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3573428.3573729","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3573428.3573729","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3573428.3573729","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053700518","display_name":"Yingyu Xu","orcid":"https://orcid.org/0000-0002-0776-9248"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yingyu Xu","raw_affiliation_strings":["Computer Science, The University of Manchester, UK"],"raw_orcid":"https://orcid.org/0000-0002-0776-9248","affiliations":[{"raw_affiliation_string":"Computer Science, The University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5053700518"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":0.1387,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5810845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1700","last_page":"1706"},"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":0.9958999752998352,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9688000082969666,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9039193391799927},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7871700525283813},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6303587555885315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6194177865982056},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.5635876655578613},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5296772718429565},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5276554822921753},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.49268537759780884},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.41121476888656616},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.395477294921875},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3702443242073059},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.13999661803245544},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.08477911353111267}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9039193391799927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871700525283813},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6303587555885315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6194177865982056},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.5635876655578613},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5296772718429565},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5276554822921753},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.49268537759780884},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.41121476888656616},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.395477294921875},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3702443242073059},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.13999661803245544},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.08477911353111267},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3573428.3573729","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3573428.3573729","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3573428.3573729","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3573428.3573729","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3573428.3573729","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3573428.3573729","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4327521011.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2434014514","https://openalex.org/W2604382266","https://openalex.org/W2736601468","https://openalex.org/W2776133043","https://openalex.org/W2889694290","https://openalex.org/W2963871073","https://openalex.org/W3016488666","https://openalex.org/W3216772467","https://openalex.org/W4206566959","https://openalex.org/W4210266050","https://openalex.org/W4226092483","https://openalex.org/W6754616581"],"related_works":["https://openalex.org/W3153786280","https://openalex.org/W2352650970","https://openalex.org/W2171010636","https://openalex.org/W3127551068","https://openalex.org/W1882507001","https://openalex.org/W2643884694","https://openalex.org/W2930863966","https://openalex.org/W2786230833","https://openalex.org/W2367922714","https://openalex.org/W1976483367"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,7,69],"is":[2,39,60],"a":[3,36],"field":[4],"of":[5,16,75,87,89],"machine":[6],"that":[8],"focuses":[9],"on":[10],"intelligent":[11,20],"agents,":[12],"primarily":[13],"the":[14,24,44,49,72,76,85,90],"concept":[15],"what":[17],"actions":[18],"an":[19],"agent":[21],"takes":[22],"in":[23],"environment":[25],"to":[26,47,83],"maximize":[27],"cumulative":[28],"reward.":[29],"In":[30],"environments":[31],"where":[32],"rewards":[33],"are":[34],"scarce,":[35],"manual":[37],"approach":[38],"necessary.":[40],"However,":[41],"manually":[42],"designing":[43],"reward":[45],"function":[46],"meet":[48],"desired":[50],"behavior":[51],"can":[52],"be":[53],"very":[54,57],"complicated.":[55],"A":[56],"useful":[58],"solution":[59],"Imitation":[61],"Learning":[62],"(IL).":[63],"This":[64],"paper":[65],"proposes":[66],"two":[67],"reinforcement":[68],"algorithms":[70],"for":[71],"basic":[73],"scene":[74],"VizDoom":[77],"video":[78],"game,":[79],"and":[80],"uses":[81],"IL":[82],"improve":[84],"performance":[86],"one":[88],"models.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2025-10-10T00:00:00"}