{"id":"https://openalex.org/W2791410145","doi":"https://doi.org/10.48550/arxiv.1803.08456","title":"Deep Reinforcement Learning with Model Learning and Monte Carlo Tree Search in Minecraft","display_name":"Deep Reinforcement Learning with Model Learning and Monte Carlo Tree Search in Minecraft","publication_year":2018,"publication_date":"2018-03-22","ids":{"openalex":"https://openalex.org/W2791410145","doi":"https://doi.org/10.48550/arxiv.1803.08456","mag":"2791410145"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1803.08456","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.08456","pdf_url":"https://arxiv.org/pdf/1803.08456","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/1803.08456","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059374858","display_name":"Stephan Alaniz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alaniz, Stephan","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science Technische Universit\u00e4t Berlin Berlin , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science Technische Universit\u00e4t Berlin Berlin , Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5059374858"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":19,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9634000062942505,"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":0.9634000062942505,"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":0.03620000183582306,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":9.999999747378752e-05,"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/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.8159999847412109},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.9779999852180481},{"id":"https://openalex.org/keywords/minecraft","display_name":"Minecraft","score":0.8379999995231628},{"id":"https://openalex.org/keywords/first-person-view","display_name":"first-person view","score":0.5600000023841858},{"id":"https://openalex.org/keywords/training-sample-efficiency","display_name":"training sample efficiency","score":0.699999988079071},{"id":"https://openalex.org/keywords/action-planning","display_name":"action planning","score":0.531000018119812},{"id":"https://openalex.org/keywords/deep-q-network-comparison","display_name":"deep Q-network comparison","score":0.7099999785423279}],"concepts":[{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.9077960848808289},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8240575790405273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7689096331596375},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6426550149917603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6095075607299805},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.587266206741333},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5521265864372253},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5430213809013367},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.46455997228622437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43939775228500366},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.4241981506347656},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41378965973854065},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27596166729927063},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.2349727749824524},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10638049244880676},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08096587657928467},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1803.08456","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.08456","pdf_url":"https://arxiv.org/pdf/1803.08456","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.1803.08456","doi":"https://doi.org/10.48550/arxiv.1803.08456","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1803.08456","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.08456","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.08456","pdf_url":"https://arxiv.org/pdf/1803.08456","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2791410145.pdf","grobid_xml":"https://content.openalex.org/works/W2791410145.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1625390266","https://openalex.org/W1714211023","https://openalex.org/W2133993682","https://openalex.org/W2145339207","https://openalex.org/W2151210636","https://openalex.org/W2260756217","https://openalex.org/W2418628973","https://openalex.org/W2480004914","https://openalex.org/W2962841471"],"related_works":["https://openalex.org/W3012086196","https://openalex.org/W7008599808","https://openalex.org/W3040761260","https://openalex.org/W7007600712","https://openalex.org/W2804460413","https://openalex.org/W2418628973","https://openalex.org/W2766688757","https://openalex.org/W4226354562","https://openalex.org/W2788049526","https://openalex.org/W2808335646"],"abstract_inverted_index":{"Deep":[0,106],"reinforcement":[1],"learning":[2,24],"has":[3],"been":[4],"successfully":[5],"applied":[6],"to":[7,34,79,89,104],"several":[8],"visual-input":[9],"tasks":[10],"using":[11],"model-free":[12],"methods.":[13],"In":[14],"this":[15,77],"paper,":[16],"we":[17],"propose":[18],"a":[19,25,36,70],"model-based":[20,98],"approach":[21,99],"that":[22],"combines":[23],"DNN-based":[26],"transition":[27,43],"model":[28,44,78],"with":[29],"Monte":[30,71],"Carlo":[31,72],"tree":[32,73],"search":[33,74],"solve":[35],"block-placing":[37],"task":[38,94],"in":[39,95],"Minecraft.":[40],"Our":[41],"learned":[42],"predicts":[45],"the":[46,50,56,61,66,81,87,92,101,105],"next":[47],"frame":[48],"and":[49,65],"rewards":[51],"one":[52],"step":[53],"ahead":[54],"given":[55],"last":[57],"four":[58],"frames":[59],"of":[60,84],"agent's":[62],"first-person-view":[63],"image":[64],"current":[67],"action.":[68],"Then":[69],"algorithm":[75],"uses":[76],"plan":[80],"best":[82],"sequence":[83],"actions":[85],"for":[86],"agent":[88],"perform.":[90],"On":[91],"proposed":[93],"Minecraft,":[96],"our":[97],"reaches":[100],"performance":[102],"comparable":[103],"Q-Network's,":[107],"but":[108],"learns":[109],"faster":[110],"and,":[111],"thus,":[112],"is":[113],"more":[114],"training":[115],"sample":[116],"efficient.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2018-03-29T00:00:00"}