{"id":"https://openalex.org/W2944895663","doi":null,"title":"TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning","display_name":"TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning","publication_year":2019,"publication_date":"2019-05-24","ids":{"openalex":"https://openalex.org/W2944895663","mag":"2944895663"},"language":"en","primary_location":{"id":"pmh:oai:eprints.gla.ac.uk:212298","doi":null,"is_oa":true,"landing_page_url":"http://eprints.gla.ac.uk/212298/","pdf_url":"http://proceedings.mlr.press/v97/adel19a.html","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj"],"host_organization":"https://openalex.org/I4405259220","host_organization_name":"Institut Agama Islam Negeri Langsa","host_organization_lineage":["https://openalex.org/I4405259220"],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://proceedings.mlr.press/v97/adel19a.html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051625926","display_name":"Tameem Adel","orcid":"https://orcid.org/0000-0003-1835-9225","observed_orcids":["https://orcid.org/0000-0003-1835-9225"]},"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":"Tameem Adel","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-1835-9225","affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042278493","display_name":"Adrian Weller","orcid":"https://orcid.org/0000-0003-1915-7158","observed_orcids":["https://orcid.org/0000-0003-1915-7158"]},"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":"Adrian Weller","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-1915-7158","affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.0813,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.25661041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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"}},{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","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/probabilistic-graphical-models","display_name":"probabilistic graphical models","score":0.7229999899864197},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9229999780654907},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.7670000195503235},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.8870000243186951},{"id":"https://openalex.org/keywords/mutual-information","display_name":"mutual information","score":0.9470000267028809},{"id":"https://openalex.org/keywords/intrinsic-rewards","display_name":"intrinsic rewards","score":0.6460000276565552},{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.7950000166893005},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.7929999828338623},{"id":"https://openalex.org/keywords/inference-efficiency","display_name":"inference efficiency","score":0.5130000114440918}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8030574321746826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508019208908081},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.7196732759475708},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.6072206497192383},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5886540412902832},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5689100623130798},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5416294932365417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5379242897033691},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.4594365954399109},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09106412529945374},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:eprints.gla.ac.uk:212298","doi":null,"is_oa":true,"landing_page_url":"http://eprints.gla.ac.uk/212298/","pdf_url":"http://proceedings.mlr.press/v97/adel19a.html","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj"],"host_organization":"https://openalex.org/I4405259220","host_organization_name":"Institut Agama Islam Negeri Langsa","host_organization_lineage":["https://openalex.org/I4405259220"],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"},{"id":"mag:2944895663","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v97/adel19a/adel19a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:212298","doi":null,"is_oa":true,"landing_page_url":"http://eprints.gla.ac.uk/212298/","pdf_url":"http://proceedings.mlr.press/v97/adel19a.html","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj"],"host_organization":"https://openalex.org/I4405259220","host_organization_name":"Institut Agama Islam Negeri Langsa","host_organization_lineage":["https://openalex.org/I4405259220"],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319993","display_name":"Leverhulme Trust","ror":"https://ror.org/012mzw131"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2944895663.pdf","grobid_xml":"https://content.openalex.org/works/W2944895663.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W114565888","https://openalex.org/W198337890","https://openalex.org/W1499669280","https://openalex.org/W1529094214","https://openalex.org/W1578521162","https://openalex.org/W1617641394","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W2026659355","https://openalex.org/W2059503215","https://openalex.org/W2080039641","https://openalex.org/W2098774185","https://openalex.org/W2107464055","https://openalex.org/W2107662876","https://openalex.org/W2107726111","https://openalex.org/W2109910161","https://openalex.org/W2120340025","https://openalex.org/W2121517924","https://openalex.org/W2173248099","https://openalex.org/W2188233853","https://openalex.org/W2211399972","https://openalex.org/W2553882142","https://openalex.org/W2557579533","https://openalex.org/W2596982695","https://openalex.org/W2609650878","https://openalex.org/W2736601468","https://openalex.org/W2776365419","https://openalex.org/W2781726626","https://openalex.org/W2785342287","https://openalex.org/W2785542505","https://openalex.org/W2785738552","https://openalex.org/W2788741142","https://openalex.org/W2796206912","https://openalex.org/W2799151646","https://openalex.org/W2803390034","https://openalex.org/W2806029332","https://openalex.org/W2808381151","https://openalex.org/W2885550588","https://openalex.org/W2898757087","https://openalex.org/W2899205164","https://openalex.org/W2920215304","https://openalex.org/W2963145887","https://openalex.org/W2963581679","https://openalex.org/W3011120880","https://openalex.org/W3037207827","https://openalex.org/W6998967213"],"related_works":["https://openalex.org/W7096846235","https://openalex.org/W3200466256","https://openalex.org/W2181867278","https://openalex.org/W6959605043","https://openalex.org/W7167730938","https://openalex.org/W2110292307","https://openalex.org/W2804673281","https://openalex.org/W6922792536","https://openalex.org/W7095548483","https://openalex.org/W2292364897"],"abstract_inverted_index":{"One":[0],"of":[1,24,91],"the":[2,21,75,83],"challenges":[3],"to":[4,35,57,118],"reinforcement":[5],"learning":[6],"(RL)":[7],"is":[8,105,115],"scalable":[9],"transferability":[10],"among":[11],"complex":[12],"tasks.":[13],"Incorporating":[14],"a":[15,28,47,92,98,106],"graphical":[16,69],"model":[17,70],"(GM),":[18],"along":[19],"with":[20],"rich":[22],"family":[23],"related":[25],"methods,":[26],"as":[27,39],"basis":[29],"for":[30],"RL":[31,50,87],"frameworks":[32],"provides":[33],"potential":[34],"address":[36],"issues":[37],"such":[38],"transferability,":[40],"generalisation":[41,59],"and":[42,60,67,85,97,130],"exploration.":[43],"Here":[44],"we":[45,73],"propose":[46],"flexible":[48,116],"GM-based":[49],"framework":[51,71,114],"which":[52],"leverages":[53],"efficient":[54],"inference":[55],"procedures":[56],"enhance":[58],"transfer":[61],"power.":[62,132],"In":[63,101],"our":[64,78,112],"proposed":[65],"transferable":[66],"information-based":[68,80],"\u2018TibGM\u2019,":[72],"show":[74],"equivalence":[76],"between":[77],"mutual":[79],"objective":[81,89],"in":[82],"GM,":[84],"an":[86],"consolidated":[88],"consisting":[90],"standard":[93],"reward":[94,110],"maximisation":[95],"target":[96],"generalisation/transfer":[99],"objective.":[100],"settings":[102],"where":[103],"there":[104],"sparse":[107],"or":[108],"deceptive":[109],"signal,":[111],"TibGM":[113],"enough":[117],"incorporate":[119],"exploration":[120,131],"bonuses":[121],"depicting":[122],"intrinsic":[123],"rewards.":[124],"We":[125],"empirically":[126],"verify":[127],"improved":[128],"performance":[129]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-05-29T00:00:00"}