{"id":"https://openalex.org/W4392904363","doi":"https://doi.org/10.1109/icassp48485.2024.10447123","title":"Leveraging Visual Handicaps for Text-Based Reinforcement Learning","display_name":"Leveraging Visual Handicaps for Text-Based Reinforcement Learning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904363","doi":"https://doi.org/10.1109/icassp48485.2024.10447123"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447123","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5000750466","display_name":"Subhajit Chaudhury","orcid":"https://orcid.org/0000-0003-3435-2584"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Subhajit Chaudhury","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104188415","display_name":"Keerthiram Murugesan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keerthiram Murugesan","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043509194","display_name":"Thomas Carta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Carta","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060691179","display_name":"Kartik Talamadupula","orcid":"https://orcid.org/0000-0002-4628-3785"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kartik Talamadupula","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049672783","display_name":"Michiaki Tatsubori","orcid":"https://orcid.org/0000-0003-2537-700X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michiaki Tatsubori","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]}],"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":"33","issue":null,"first_page":"12376","last_page":"12380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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":0.9975000023841858,"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/T10028","display_name":"Topic Modeling","score":0.984000027179718,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9793000221252441,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8465921878814697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8240792751312256},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7451249957084656},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7017107009887695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6193103194236755},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.588219165802002},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49366292357444763},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43908604979515076},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38968104124069214},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34740954637527466}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8465921878814697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8240792751312256},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7451249957084656},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7017107009887695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6193103194236755},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.588219165802002},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49366292357444763},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43908604979515076},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38968104124069214},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34740954637527466},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447123","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1916087103","https://openalex.org/W1934909785","https://openalex.org/W2001781545","https://openalex.org/W2621150162","https://openalex.org/W2736601468","https://openalex.org/W2765123421","https://openalex.org/W2784198807","https://openalex.org/W2810346659","https://openalex.org/W2902391430","https://openalex.org/W2964179661","https://openalex.org/W2996887765","https://openalex.org/W2998557583","https://openalex.org/W3035850279","https://openalex.org/W3092241275","https://openalex.org/W3099204253","https://openalex.org/W3167131563","https://openalex.org/W4288263337","https://openalex.org/W6638847296","https://openalex.org/W6741002519","https://openalex.org/W6779638344","https://openalex.org/W6841120134"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"We":[0,71,120],"introduce":[1],"VisualHandicaps,":[2],"a":[3,123],"novel":[4],"benchmark":[5],"environment":[6,81],"for":[7,61,136],"the":[8,46,62,111,118],"systematic":[9,89],"analysis":[10,125],"of":[11,37,49,55,66,107,113,126],"interactive":[12],"text-based":[13,144],"reinforcement":[14],"learning":[15],"(TBRL)":[16],"agents":[17,51,142],"by":[18],"providing":[19,29],"visual":[20,90],"handicaps.":[21],"Unlike":[22],"previous":[23,98],"TBRL":[24],"environments,":[25],"which":[26,129],"focus":[27],"on":[28,143],"additional":[30],"textual":[31,58,94,103],"information":[32],"to":[33,44,116,132],"measure":[34],"agent":[35,86],"understanding":[36],"sequential":[38],"natural":[39],"language":[40],"information,":[41,59],"VisualHandicaps":[42],"seeks":[43],"improve":[45],"generalization":[47],"ability":[48],"RL":[50,141],"using":[52,87],"varying":[53],"details":[54],"maps":[56],"and":[57,64,69,76,82,110],"allowing":[60],"study":[63],"demonstration":[65],"robust":[67],"planning":[68],"self-localization.":[70],"provide":[72,122],"automatically":[73],"generated":[74],"variations":[75],"difficulty":[77],"levels":[78],"in":[79,105,140],"our":[80,88],"show":[83],"that":[84],"an":[85],"handicaps":[91],"along":[92],"with":[93],"observation":[95],"generally":[96],"outperforms":[97],"methods":[99],"(that":[100],"use":[101],"only":[102],"handicaps)":[104],"terms":[106],"success":[108],"rate":[109],"number":[112],"steps":[114],"required":[115],"reach":[117],"goal.":[119],"also":[121],"detailed":[124],"each":[127],"handicap,":[128],"we":[130],"believe":[131],"be":[133],"important":[134],"findings":[135],"driving":[137],"future":[138],"improvements":[139],"applications.":[145]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}