{"id":"https://openalex.org/W3176973640","doi":"https://doi.org/10.1609/aaai.v35i18.17917","title":"RL Generalization in a Theory of Mind Game Through a Sleep Metaphor (Student Abstract)","display_name":"RL Generalization in a Theory of Mind Game Through a Sleep Metaphor (Student Abstract)","publication_year":2021,"publication_date":"2021-05-18","ids":{"openalex":"https://openalex.org/W3176973640","doi":"https://doi.org/10.1609/aaai.v35i18.17917","mag":"3176973640"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v35i18.17917","doi":"https://doi.org/10.1609/aaai.v35i18.17917","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i18.17917","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/17917/17722","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/17917/17722","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006638341","display_name":"Tyler Malloy","orcid":"https://orcid.org/0000-0003-2512-984X","observed_orcids":["https://orcid.org/0000-0003-2512-984X"]},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tyler Malloy","raw_affiliation_strings":["Rensselaer Polytechnic Institute\nIBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute\nIBM Research AI","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074288533","display_name":"Tim Klinger","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Klinger","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348892","display_name":"Miao Liu","orcid":"https://orcid.org/0000-0002-1648-8325","observed_orcids":["https://orcid.org/0000-0002-1648-8325","https://orcid.org/0000-0002-6650-9972"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miao Liu","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113551673","display_name":"Gerald J. Tesauro","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Tesauro","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037927240","display_name":"Matthew Riemer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Riemer","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038964785","display_name":"Chris R. Sims","orcid":"https://orcid.org/0000-0002-3110-1686","observed_orcids":["https://orcid.org/0000-0002-3110-1686"]},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris R. Sims","raw_affiliation_strings":["Rensselaer Polytechnic Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.094,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.26490361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":"35","issue":"18","first_page":"15841","last_page":"15842"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7886000275611877,"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":0.7886000275611877,"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":0.17970000207424164,"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/T11031","display_name":"Game Theory and Applications","score":0.004399999976158142,"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/theory-of-mind","display_name":"theory of mind","score":0.7390000224113464},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.6309999823570251},{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.8669999837875366},{"id":"https://openalex.org/keywords/information-theoretic-constraints","display_name":"information-theoretic constraints","score":0.847000002861023},{"id":"https://openalex.org/keywords/policy-training","display_name":"policy training","score":0.32199999690055847}],"concepts":[{"id":"https://openalex.org/C2778311575","wikidata":"https://www.wikidata.org/wiki/Q18534","display_name":"Metaphor","level":2,"score":0.8911197185516357},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8453797101974487},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6662486791610718},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6007202863693237},{"id":"https://openalex.org/C2775841894","wikidata":"https://www.wikidata.org/wiki/Q4683692","display_name":"Sleep (system call)","level":2,"score":0.5328733325004578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4899879992008209},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.45358943939208984},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.40323084592819214},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.363552451133728},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34124284982681274},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.31401440501213074},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.19296616315841675},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.1614108681678772},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12172448635101318},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06703269481658936},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v35i18.17917","doi":"https://doi.org/10.1609/aaai.v35i18.17917","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i18.17917","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/17917/17722","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v35i18.17917","doi":"https://doi.org/10.1609/aaai.v35i18.17917","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i18.17917","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/17917/17722","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3176973640.pdf","grobid_xml":"https://content.openalex.org/works/W3176973640.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2260756217","https://openalex.org/W2556958149","https://openalex.org/W2913781869","https://openalex.org/W3043264569"],"related_works":["https://openalex.org/W3124474845","https://openalex.org/W3128901210","https://openalex.org/W2608300356","https://openalex.org/W2993490502","https://openalex.org/W7104663241","https://openalex.org/W7133318306","https://openalex.org/W4414900919","https://openalex.org/W3092931668","https://openalex.org/W7125826601","https://openalex.org/W7171125490"],"abstract_inverted_index":{"Training":[0],"agents":[1],"to":[2,35],"learn":[3],"efficiently":[4],"in":[5,19,37,112],"multi-agent":[6],"environments":[7],"can":[8,47],"benefit":[9],"from":[10,94],"the":[11,25,72,90],"explicit":[12,118],"modelling":[13],"of":[14,71,120],"other":[15,121],"agent's":[16,91,122],"beliefs,":[17],"especially":[18],"complex":[20,114],"limited-information":[21],"games":[22],"such":[23],"as":[24,83,85],"Hanabi":[26,73],"card":[27],"game.":[28,74],"However,":[29],"generalization":[30],"is":[31],"also":[32],"highly":[33],"relevant":[34],"performance":[36,98],"these":[38],"games,":[39],"though":[40],"model":[41,60],"comparisons":[42],"at":[43],"large":[44],"training":[45,81],"timescales":[46],"be":[48],"difficult.":[49],"In":[50],"this":[51,55,100],"work,":[52],"we":[53],"address":[54],"by":[56],"introducing":[57],"a":[58,63,67,105],"novel":[59],"trained":[61],"using":[62,109],"sleep":[64,76],"metaphor":[65,77],"on":[66,89],"reduced":[68],"complexity":[69],"version":[70],"This":[75],"consists":[78],"an":[79,86],"altered":[80],"regiment,":[82],"well":[84],"information-theoretic":[87],"constraint":[88],"policy.":[92],"Results":[93],"experimentation":[95],"demonstrate":[96],"improved":[97],"through":[99],"sleep-metaphor":[101],"method,":[102],"and":[103],"provide":[104],"promising":[106],"motivation":[107],"for":[108],"similar":[110],"techniques":[111],"more":[113],"methods":[115],"that":[116],"incorporate":[117],"models":[119],"beliefs.":[123]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-07-05T00:00:00"}