{"id":"https://openalex.org/W4391116681","doi":"https://doi.org/10.1609/aaaiss.v2i1.27670","title":"Modifying RL Policies with Imagined Actions: How Predictable Policies Can Enable Users to Perform Novel Tasks","display_name":"Modifying RL Policies with Imagined Actions: How Predictable Policies Can Enable Users to Perform Novel Tasks","publication_year":2024,"publication_date":"2024-01-22","ids":{"openalex":"https://openalex.org/W4391116681","doi":"https://doi.org/10.1609/aaaiss.v2i1.27670"},"language":"en","primary_location":{"id":"doi:10.1609/aaaiss.v2i1.27670","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaaiss.v2i1.27670","pdf_url":"https://ojs.aaai.org/index.php/AAAI-SS/article/download/27670/27443","source":{"id":"https://openalex.org/S4389157828","display_name":"Proceedings of the AAAI Symposium Series","issn_l":"2994-4317","issn":["2994-4317"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Symposium Series","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI-SS/article/download/27670/27443","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070000164","display_name":"Isaac Sheidlower","orcid":"https://orcid.org/0009-0004-4487-8357"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Isaac Sheidlower","raw_affiliation_strings":["Tufts University, Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University, Department of Computer Science","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017028387","display_name":"Reuben M. Aronson","orcid":"https://orcid.org/0000-0002-8615-3715"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reuben Aronson","raw_affiliation_strings":["Tufts University, Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University, Department of Computer Science","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077011363","display_name":"Elaine Schaertl Short","orcid":"https://orcid.org/0000-0002-4789-9979"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elaine Short","raw_affiliation_strings":["Tufts University, Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University, Department of Computer Science","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I121934306"],"apc_list":null,"apc_paid":null,"fwci":0.7112,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6541147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"2","issue":"1","first_page":"192","last_page":"197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9663000106811523,"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":0.9663000106811523,"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/leverage","display_name":"Leverage (statistics)","score":0.7684780359268188},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7320351004600525},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7224258184432983},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.672057032585144},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6381233930587769},{"id":"https://openalex.org/keywords/teleoperation","display_name":"Teleoperation","score":0.6203799843788147},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.55727618932724},{"id":"https://openalex.org/keywords/autonomy","display_name":"Autonomy","score":0.5240764021873474},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49338236451148987},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4738978445529938},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.420421838760376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4042384624481201},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12880074977874756}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7684780359268188},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7320351004600525},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7224258184432983},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.672057032585144},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6381233930587769},{"id":"https://openalex.org/C161759796","wikidata":"https://www.wikidata.org/wiki/Q3982902","display_name":"Teleoperation","level":3,"score":0.6203799843788147},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.55727618932724},{"id":"https://openalex.org/C65414064","wikidata":"https://www.wikidata.org/wiki/Q484105","display_name":"Autonomy","level":2,"score":0.5240764021873474},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49338236451148987},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4738978445529938},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.420421838760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4042384624481201},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12880074977874756},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaaiss.v2i1.27670","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaaiss.v2i1.27670","pdf_url":"https://ojs.aaai.org/index.php/AAAI-SS/article/download/27670/27443","source":{"id":"https://openalex.org/S4389157828","display_name":"Proceedings of the AAAI Symposium Series","issn_l":"2994-4317","issn":["2994-4317"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Symposium Series","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaaiss.v2i1.27670","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaaiss.v2i1.27670","pdf_url":"https://ojs.aaai.org/index.php/AAAI-SS/article/download/27670/27443","source":{"id":"https://openalex.org/S4389157828","display_name":"Proceedings of the AAAI Symposium Series","issn_l":"2994-4317","issn":["2994-4317"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Symposium Series","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391116681.pdf"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1497716120","https://openalex.org/W1967904302","https://openalex.org/W2105925198","https://openalex.org/W2107726111","https://openalex.org/W2594775242","https://openalex.org/W2626804490","https://openalex.org/W2745868649","https://openalex.org/W2803697594","https://openalex.org/W2904246096","https://openalex.org/W2930863966","https://openalex.org/W2963366811","https://openalex.org/W2965916140","https://openalex.org/W3094060111","https://openalex.org/W3119172160","https://openalex.org/W3128055785","https://openalex.org/W3134383769","https://openalex.org/W3154226752","https://openalex.org/W3165749036","https://openalex.org/W3169972599","https://openalex.org/W3188067267","https://openalex.org/W3194461566","https://openalex.org/W3198115943","https://openalex.org/W3199185513","https://openalex.org/W3205597769","https://openalex.org/W3212554354","https://openalex.org/W4200102537","https://openalex.org/W4210659164","https://openalex.org/W4223977507","https://openalex.org/W4224130159","https://openalex.org/W4224912544","https://openalex.org/W4226164612","https://openalex.org/W4248056173","https://openalex.org/W4285077530","https://openalex.org/W4295124108","https://openalex.org/W4296414573","https://openalex.org/W4297812239","https://openalex.org/W4311250086","https://openalex.org/W4312772252","https://openalex.org/W4318953217","https://openalex.org/W4321392130","https://openalex.org/W4323572061","https://openalex.org/W4367190577","https://openalex.org/W4383097638","https://openalex.org/W4385403839","https://openalex.org/W4385430539","https://openalex.org/W6629839821","https://openalex.org/W6644813291","https://openalex.org/W6648369751","https://openalex.org/W6675851438","https://openalex.org/W6676007687","https://openalex.org/W6693275029","https://openalex.org/W6742958495","https://openalex.org/W6751494907","https://openalex.org/W6796293393","https://openalex.org/W6802647179","https://openalex.org/W6848841101","https://openalex.org/W6850503672","https://openalex.org/W6907649514","https://openalex.org/W6929389603"],"related_works":["https://openalex.org/W1923069992","https://openalex.org/W2160982102","https://openalex.org/W2048862765","https://openalex.org/W2768698792","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"It":[0],"is":[1,52,112],"crucial":[2],"that":[3,142],"users":[4],"are":[5],"empowered":[6],"to":[7,14,26,35,46,56,105,147,155],"use":[8,36],"the":[9,19,37,54,62,69,74,93,100,110,117,120],"functionalities":[10],"of":[11,43,59,61,119,151],"a":[12,27,88,96,108,152],"robot":[13,32,94],"creatively":[15],"solve":[16],"problems":[17],"on":[18],"fly.":[20],"A":[21],"user":[22,55,111],"who":[23],"has":[24],"access":[25],"Reinforcement":[28],"Learning":[29],"(RL)":[30],"based":[31],"may":[33,81,91],"want":[34],"robot's":[38,63,153],"autonomy":[39],"and":[40,131,144],"their":[41,149],"knowledge":[42],"its":[44],"behavior":[45,154],"complete":[47],"new":[48,157],"tasks.":[49,158],"One":[50],"way":[51,109],"for":[53,140],"take":[57],"control":[58,90],"some":[60],"action":[64],"space":[65],"through":[66],"teleoperation":[67],"while":[68],"RL":[70,79],"policy":[71,80],"simultaneously":[72],"controls":[73],"rest.":[75],"However,":[76],"an":[77,137],"out-of-the-box":[78],"not":[82,113],"readily":[83],"facilitate":[84],"this.":[85],"For":[86],"example,":[87],"user's":[89,121,146],"bring":[92],"into":[95],"failure":[97],"state":[98],"from":[99],"policy's":[101],"perspective,":[102],"causing":[103],"it":[104],"act":[106],"in":[107],"familiar":[114],"with,":[115],"hindering":[116],"success":[118],"desired":[122],"task.":[123],"In":[124],"this":[125,129],"work,":[126],"we":[127],"formalize":[128],"problem":[130,143],"present":[132],"Imaginary":[133],"Out-of-Distribution":[134],"Actions,":[135],"IODA,":[136],"initial":[138],"algorithm":[139],"addressing":[141],"empowering":[145],"leverage":[148],"expectation":[150],"accomplish":[156]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}