{"id":"https://openalex.org/W2889169285","doi":null,"title":"ExpIt-OOS: Towards Learning from Planning in Imperfect Information Games.","display_name":"ExpIt-OOS: Towards Learning from Planning in Imperfect Information Games.","publication_year":2018,"publication_date":"2018-08-30","ids":{"openalex":"https://openalex.org/W2889169285","mag":"2889169285"},"language":"en","primary_location":{"id":"mag:2889169285","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1808.10120.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1808.10120.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028608452","display_name":"Andy Kitchen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andy Kitchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5040291058","display_name":"Michela Benedetti","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michela Benedetti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9994999766349792,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9994999766349792,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0003000000142492354,"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":0.0,"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/imperfect-information-games","display_name":"imperfect information games","score":0.9649999737739563},{"id":"https://openalex.org/keywords/alphazero","display_name":"AlphaZero","score":0.7680000066757202},{"id":"https://openalex.org/keywords/self-play","display_name":"self-play","score":0.5080000162124634},{"id":"https://openalex.org/keywords/game-ai","display_name":"game AI","score":0.4009999930858612}],"concepts":[{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.8650810122489929},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.8225101232528687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745988130569458},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6240389347076416},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.6053550839424133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49081549048423767},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43061283230781555},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0906679630279541},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08176916837692261},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2889169285","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1808.10120.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2889169285","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1808.10120.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1595285848","https://openalex.org/W2168356773","https://openalex.org/W2187559597","https://openalex.org/W2232669028","https://openalex.org/W2291772168","https://openalex.org/W2291986326","https://openalex.org/W2618097077","https://openalex.org/W2741375793","https://openalex.org/W2899771611","https://openalex.org/W2902907165"],"related_works":["https://openalex.org/W4394649275","https://openalex.org/W3116263860","https://openalex.org/W7162464841","https://openalex.org/W4378746517","https://openalex.org/W6946129445","https://openalex.org/W2187559597","https://openalex.org/W3097986043","https://openalex.org/W3130605884","https://openalex.org/W7014903614","https://openalex.org/W2965394063"],"abstract_inverted_index":{"The":[0],"current":[1],"state":[2],"of":[3,68,82],"the":[4,45,80],"art":[5],"in":[6,66,84],"playing":[7,40],"many":[8],"important":[9],"perfect":[10],"information":[11,31,42,64,95],"games,":[12],"including":[13],"Chess":[14],"and":[15,19,33,49,89],"Go,":[16],"combines":[17],"planning":[18,90],"deep":[20],"reinforcement":[21],"learning":[22,88],"with":[23],"self-play.":[24],"We":[25,53],"extend":[26],"this":[27],"approach":[28,38],"to":[29,39,78],"imperfect":[30,41,63,94],"games":[32,43,65],"present":[34],"ExIt-OOS,":[35],"a":[36,87],"novel":[37],"within":[44],"Expert":[46],"Iteration":[47],"framework":[48],"inspired":[50],"by":[51],"AlphaZero.":[52],"use":[54],"Online":[55],"Outcome":[56],"Sampling,":[57],"an":[58],"online":[59],"search":[60],"algorithm":[61],"for":[62,93],"place":[67],"MCTS.":[69],"While":[70],"training":[71],"online,":[72],"our":[73],"neural":[74],"strategy":[75],"is":[76],"used":[77],"improve":[79],"accuracy":[81],"playouts":[83],"OOS,":[85],"allowing":[86],"feedback":[91],"loop":[92],"games.":[96]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-09-07T00:00:00"}