{"id":"https://openalex.org/W3204728086","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534127","title":"FoLaR: Foggy Latent Representations for Reinforcement Learning with Partial Observability","display_name":"FoLaR: Foggy Latent Representations for Reinforcement Learning with Partial Observability","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3204728086","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534127","mag":"3204728086"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028455101","display_name":"Hardik Meisheri","orcid":"https://orcid.org/0000-0002-9014-1098"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Hardik Meisheri","raw_affiliation_strings":["TCS Research, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, Mumbai, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045214135","display_name":"Harshad Khadilkar","orcid":"https://orcid.org/0000-0003-3601-778X"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Harshad Khadilkar","raw_affiliation_strings":["TCS Research, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, Mumbai, India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028455101"],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.14394729,"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9959999918937683,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9937999844551086,"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/observability","display_name":"Observability","score":0.8963013291358948},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8438851833343506},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7398618459701538},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.643958568572998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6056375503540039},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5945062041282654},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5836455821990967},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5264347791671753},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4880903959274292},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4775981903076172},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4584067165851593},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4489065706729889},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.44173580408096313},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4126468896865845},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15740719437599182},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08721232414245605}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.8963013291358948},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8438851833343506},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398618459701538},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.643958568572998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6056375503540039},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5945062041282654},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5836455821990967},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5264347791671753},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4880903959274292},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4775981903076172},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4584067165851593},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4489065706729889},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.44173580408096313},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4126468896865845},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15740719437599182},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08721232414245605},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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:10.1109/ijcnn52387.2021.9534127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1191599655","https://openalex.org/W1497506444","https://openalex.org/W1591992921","https://openalex.org/W1662842982","https://openalex.org/W1941445455","https://openalex.org/W1968962398","https://openalex.org/W2011418219","https://openalex.org/W2034725503","https://openalex.org/W2042830238","https://openalex.org/W2064675550","https://openalex.org/W2111680853","https://openalex.org/W2121863487","https://openalex.org/W2123542217","https://openalex.org/W2154384352","https://openalex.org/W2154997814","https://openalex.org/W2158282517","https://openalex.org/W2165150801","https://openalex.org/W2168359464","https://openalex.org/W2170296074","https://openalex.org/W2173248099","https://openalex.org/W2568646110","https://openalex.org/W2781726626","https://openalex.org/W2804380964","https://openalex.org/W2890208753","https://openalex.org/W2900152462","https://openalex.org/W2902907165","https://openalex.org/W2913238847","https://openalex.org/W2948210913","https://openalex.org/W2950533301","https://openalex.org/W2962821147","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964062135","https://openalex.org/W2970667219","https://openalex.org/W2997101648","https://openalex.org/W3022265613","https://openalex.org/W3036185205","https://openalex.org/W3093458824","https://openalex.org/W3101283005","https://openalex.org/W3125947392","https://openalex.org/W3131944163","https://openalex.org/W4287637954","https://openalex.org/W4287724327","https://openalex.org/W4288335419","https://openalex.org/W4288614690","https://openalex.org/W4289294484","https://openalex.org/W4302570325","https://openalex.org/W6627932998","https://openalex.org/W6677000785","https://openalex.org/W6678409309","https://openalex.org/W6683084483","https://openalex.org/W6684909995","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6747473740","https://openalex.org/W6750253780","https://openalex.org/W6751540476","https://openalex.org/W6754184789","https://openalex.org/W6756256016","https://openalex.org/W6756287877","https://openalex.org/W6758549464","https://openalex.org/W6758814384","https://openalex.org/W6763088550","https://openalex.org/W6779827379","https://openalex.org/W6780470247","https://openalex.org/W6784311389"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2967463586","https://openalex.org/W2765830098","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W11481024","https://openalex.org/W131709709","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"We":[0,40,118],"propose":[1,41],"a":[2],"novel":[3],"methodology":[4],"for":[5,43,63,89,115],"improving":[6],"the":[7,20,36,71,75,83,91,97,104,111,121],"rate":[8],"and":[9,74,93,136],"consistency":[10],"of":[11,23,96],"reinforcement":[12,48],"learning":[13,49,126],"in":[14,51,56,103,108,127,139,142],"partially":[15,31,57],"observable":[16,32,58],"(foggy)":[17],"environments,":[18,33],"under":[19],"broader":[21],"umbrella":[22],"robust":[24],"latent":[25,77,85],"representations.":[26],"The":[27],"present":[28],"work":[29],"addresses":[30],"which":[34],"violate":[35],"canonical":[37],"Markov":[38],"assumptions.":[39],"adaptations":[42],"any":[44],"on-policy":[45],"model-free":[46],"deep":[47],"algorithm,":[50],"order":[52],"to":[53,100,110],"improve":[54,125],"training":[55],"situations:":[59],"(i)":[60],"recurrent":[61],"layers":[62],"including":[64],"information":[65],"from":[66,82],"previous":[67],"observations,":[68],"(ii)":[69],"predicting":[70],"step":[72],"reward":[73],"next":[76],"representation":[78],"as":[79,87],"auxiliary":[80,106],"outputs":[81],"same":[84],"space":[86],"used":[88,114],"inferring":[90],"action,":[92],"(iii)":[94],"modification":[95],"loss":[98],"function":[99],"penalise":[101],"errors":[102],"two":[105],"outputs,":[107],"addition":[109],"reward-based":[112],"gradients":[113],"policy":[116],"training.":[117],"show":[119],"that":[120],"proposed":[122],"changes":[123],"substantially":[124],"several":[128],"environments":[129,145],"over":[130],"vanilla":[131],"Proximal":[132],"Policy":[133],"Optimisation":[134],"(PPO)":[135],"other":[137],"baselines":[138],"literature,":[140],"especially":[141],"known":[143],"challenging":[144],"with":[146],"hard":[147],"exploration.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}