{"id":"https://openalex.org/W4406890379","doi":"https://doi.org/10.1109/lra.2025.3535187","title":"Reinforcement Learning of Flexible Policies for Symbolic Instructions With Adjustable Mapping Specifications","display_name":"Reinforcement Learning of Flexible Policies for Symbolic Instructions With Adjustable Mapping Specifications","publication_year":2025,"publication_date":"2025-01-28","ids":{"openalex":"https://openalex.org/W4406890379","doi":"https://doi.org/10.1109/lra.2025.3535187"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3535187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3535187","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5036929872","display_name":"Wataru Hatanaka","orcid":"https://orcid.org/0009-0006-4030-5142"},"institutions":[{"id":"https://openalex.org/I24193003","display_name":"Ricoh (Japan)","ror":"https://ror.org/02h4myp42","country_code":"JP","type":"company","lineage":["https://openalex.org/I24193003"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wataru Hatanaka","raw_affiliation_strings":["Digital Strategy Division, RICOH Company, Ltd., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0006-4030-5142","affiliations":[{"raw_affiliation_string":"Digital Strategy Division, RICOH Company, Ltd., Tokyo, Japan","institution_ids":["https://openalex.org/I24193003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065798083","display_name":"Ryota YAMASHINA","orcid":null},"institutions":[{"id":"https://openalex.org/I24193003","display_name":"Ricoh (Japan)","ror":"https://ror.org/02h4myp42","country_code":"JP","type":"company","lineage":["https://openalex.org/I24193003"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryota Yamashina","raw_affiliation_strings":["Digital Strategy Division, RICOH Company, Ltd., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Strategy Division, RICOH Company, Ltd., Tokyo, Japan","institution_ids":["https://openalex.org/I24193003"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042074952","display_name":"Takamitsu Matsubara","orcid":"https://orcid.org/0000-0003-3545-4814"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takamitsu Matsubara","raw_affiliation_strings":["Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Nara, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3545-4814","affiliations":[{"raw_affiliation_string":"Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0057797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"3","first_page":"2614","last_page":"2621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7684038877487183},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6854707598686218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.642876386642456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38400647044181824},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1748279631137848},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09891378879547119}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7684038877487183},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6854707598686218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.642876386642456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38400647044181824},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1748279631137848},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09891378879547119}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3535187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3535187","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1498432697","https://openalex.org/W1540883472","https://openalex.org/W1977655452","https://openalex.org/W2023808162","https://openalex.org/W2141088850","https://openalex.org/W2736601468","https://openalex.org/W2760103357","https://openalex.org/W2899455150","https://openalex.org/W2966537673","https://openalex.org/W3037476194","https://openalex.org/W3097255974","https://openalex.org/W3142849873","https://openalex.org/W3213974477","https://openalex.org/W4212943651","https://openalex.org/W4226313597","https://openalex.org/W4286896047","https://openalex.org/W4386872349","https://openalex.org/W4394963598","https://openalex.org/W6697359928","https://openalex.org/W6741002519","https://openalex.org/W6752155926","https://openalex.org/W6752298494","https://openalex.org/W6758288215","https://openalex.org/W6766842884","https://openalex.org/W6769596995","https://openalex.org/W6775647304","https://openalex.org/W6790190981","https://openalex.org/W6790722625","https://openalex.org/W6800004206","https://openalex.org/W6803736601","https://openalex.org/W6843759960"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Symbolic":[0,124],"task":[1,179],"representation":[2],"is":[3],"a":[4,141,162,177],"powerful":[5],"tool":[6],"for":[7,119],"encoding":[8],"human":[9],"instructions":[10,15,101,135,159],"and":[11,22,81,102,175,196],"domain":[12],"knowledge.":[13],"Such":[14],"guide":[16],"robots":[17,60,71],"to":[18,40,55,73,96,186],"accomplish":[19],"diverse":[20],"objectives":[21],"meet":[23],"constraints":[24],"through":[25],"reinforcement":[26],"learning":[27,108,120],"(RL).":[28],"Most":[29],"existing":[30],"methods":[31],"are":[32],"based":[33],"on":[34,93],"fixed":[35],"mappings":[36],"from":[37,52,66],"environmental":[38],"states":[39],"symbols.":[41],"However,":[42],"in":[43,169,172,191],"inspection":[44],"tasks,":[45],"where":[46],"equipment":[47],"conditions":[48],"must":[49,61],"be":[50,146],"evaluated":[51],"multiple":[53],"perspectives":[54],"avoid":[56],"errors":[57],"of":[58,99,158],"oversight,":[59],"fulfill":[62],"the":[63,154,187],"same":[64],"symbol":[65,75],"different":[67],"states.":[68],"To":[69,110],"help":[70],"respond":[72],"flexible":[74,121],"mapping,":[76],"we":[77,115],"propose":[78],"representing":[79],"symbols":[80],"their":[82],"mapping":[83,103,170],"specifications":[84,171],"separately":[85],"within":[86],"an":[87,106,117],"RL":[88,94,207],"policy.":[89],"This":[90,131],"approach":[91,118],"imposes":[92],"policy":[95],"learn":[97],"combinations":[98],"symbolic":[100,134],"specifications,":[104],"requiring":[105],"efficient":[107],"framework.":[109],"cope":[111],"with":[112,126,194],"this":[113],"issue,":[114],"introduce":[116],"policies":[122],"called":[123],"Instructions":[125],"Adjustable":[127],"Mapping":[128],"Specifications":[129],"(SIAMS).":[130],"paper":[132],"represents":[133],"using":[136],"linear":[137],"temporal":[138],"logic":[139],"(LTL),":[140],"formal":[142],"language":[143],"that":[144,201],"can":[145],"easily":[147],"integrated":[148],"into":[149],"RL.":[150],"Our":[151],"method":[152,203],"addresses":[153],"diversified":[155],"completion":[156],"patterns":[157],"by":[160],"(1)":[161],"specification-aware":[163],"state":[164,173],"modulation,":[165],"which":[166,181],"embeds":[167],"differences":[168],"features,":[174],"(2)":[176],"symbol-number-based":[178],"curriculum,":[180],"gradually":[182],"provides":[183],"tasks":[184],"according":[185],"learning's":[188],"progress.":[189],"Evaluations":[190],"3D":[192],"simulations":[193],"discrete":[195],"continuous":[197],"action":[198],"spaces":[199],"demonstrate":[200],"our":[202],"outperforms":[204],"context-aware":[205],"multi-task":[206],"comparisons.":[208]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}