{"id":"https://openalex.org/W3199729050","doi":null,"title":"Synthesizing Policies That Account For Human Execution Errors Caused By State-Aliasing In Markov Decision Processes.","display_name":"Synthesizing Policies That Account For Human Execution Errors Caused By State-Aliasing In Markov Decision Processes.","publication_year":2021,"publication_date":"2021-09-15","ids":{"openalex":"https://openalex.org/W3199729050","mag":"3199729050"},"language":"en","primary_location":{"id":"mag:3199729050","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.07436v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.07436v2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037582330","display_name":"Sriram Gopalakrishnan","orcid":"https://orcid.org/0000-0002-6461-391X","observed_orcids":["https://orcid.org/0000-0002-6461-391X"]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Gopalakrishnan","raw_affiliation_strings":["Arizona State University**"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University**","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049064111","display_name":"Mudit Verma","orcid":"https://orcid.org/0009-0008-7191-4519","observed_orcids":["https://orcid.org/0009-0008-7191-4519","https://orcid.org/0000-0003-4524-2102"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mudit Verma","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4524-2102","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023323170","display_name":"Subbarao Kambhampati B","orcid":"https://orcid.org/0000-0002-9069-0265","observed_orcids":["https://orcid.org/0000-0002-9069-0265"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Subbarao Kambhampati","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9069-0265","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7329000234603882,"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":0.7329000234603882,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.23440000414848328,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.003599999938160181,"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/markov-decision-process","display_name":"Markov decision process","score":0.843999981880188},{"id":"https://openalex.org/keywords/state-uncertainty","display_name":"state uncertainty","score":0.8080000281333923},{"id":"https://openalex.org/keywords/policy-synthesis","display_name":"policy synthesis","score":0.4390000104904175},{"id":"https://openalex.org/keywords/execution-delay","display_name":"execution delay","score":0.6880000233650208},{"id":"https://openalex.org/keywords/inaction","display_name":"inaction","score":0.5860000252723694},{"id":"https://openalex.org/keywords/hill-climbing","display_name":"hill climbing","score":0.8109999895095825},{"id":"https://openalex.org/keywords/branch-and-bound","display_name":"branch and bound","score":0.9860000014305115},{"id":"https://openalex.org/keywords/human-subjects-research","display_name":"human subjects research","score":0.6140000224113464},{"id":"https://openalex.org/keywords/grid-world","display_name":"grid world","score":0.8949999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8096885681152344},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6998779773712158},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.654106080532074},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5072597861289978},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4880129396915436},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47809168696403503},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.47359779477119446},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4728836417198181},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.38174206018447876},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3413897156715393},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33688369393348694},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3241257071495056},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2650356590747833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23479312658309937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20211169123649597},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10788685083389282},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08514276146888733},{"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/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3199729050","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.07436v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3199729050","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.07436v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W80823096","https://openalex.org/W1531218190","https://openalex.org/W1547820416","https://openalex.org/W1687873425","https://openalex.org/W1701684472","https://openalex.org/W1978942630","https://openalex.org/W2048984163","https://openalex.org/W2052117683","https://openalex.org/W2075754841","https://openalex.org/W2119896685","https://openalex.org/W2127816222","https://openalex.org/W2143458217","https://openalex.org/W2164878629","https://openalex.org/W2405447529","https://openalex.org/W2947643884","https://openalex.org/W3172135444"],"related_works":["https://openalex.org/W4286974834","https://openalex.org/W7095331133","https://openalex.org/W3123322931","https://openalex.org/W4394672832","https://openalex.org/W1650504995","https://openalex.org/W7098018723","https://openalex.org/W7124135461","https://openalex.org/W2234060732","https://openalex.org/W7095450663","https://openalex.org/W7096648162"],"abstract_inverted_index":{"When":[0],"humans":[1,196],"are":[2,199],"given":[3],"a":[4,24,31,34,56,88,95,99,105,131,156,171],"policy":[5,11,32,49,64,112,150,193],"to":[6,36,39,107,124,135,161],"execute,":[7],"there":[8,19],"can":[9],"be":[10],"execution":[12,17,80,82,113,194],"errors":[13,114],"and":[14,81,115,158,174],"deviations":[15],"in":[16,22,43,94,170],"if":[18,189],"is":[20,51,66,128],"uncertainty":[21],"identifying":[23],"state.":[25],"So":[26],"an":[27],"algorithm":[28,134,160],"that":[29,50,65,91,140,187],"computes":[30],"for":[33,87,137,142],"human":[35,57,89,185],"execute":[37],"ought":[38],"consider":[40,75],"these":[41,143],"effects":[42],"its":[44],"computations.":[45],"An":[46],"optimal":[47,164],"MDP":[48],"poorly":[52],"executed":[53,67],"(because":[54],"of":[55,78,111,117,178],"agent)":[58],"maybe":[59],"much":[60],"worse":[61],"than":[62],"another":[63],"with":[68,155],"fewer":[69],"errors.":[70,144],"In":[71],"this":[72],"paper,":[73],"we":[74],"the":[76,109,148,163,176,179],"problems":[77],"erroneous":[79],"delay":[83],"when":[84],"computing":[85],"policies":[86,139],"agent":[90],"would":[92],"act":[93],"setting":[96],"modeled":[97],"by":[98,130,152,195],"Markov":[100],"Decision":[101],"Process.":[102],"We":[103,145,166,182],"present":[104,184],"framework":[106],"model":[108],"likelihood":[110,116],"non-policy":[118],"actions":[119],"like":[120],"inaction":[121],"(delays)":[122],"due":[123],"state":[125],"uncertainty.":[126],"This":[127],"followed":[129],"hill":[132,153],"climbing":[133,154],"search":[136],"good":[138],"account":[141],"then":[146],"use":[147],"best":[149],"found":[151],"branch":[157],"bound":[159],"find":[162],"policy.":[165],"show":[167],"experimental":[168],"results":[169],"Gridworld":[172],"domain":[173],"analyze":[175],"performance":[177],"two":[180],"algorithms.":[181],"also":[183],"studies":[186],"verify":[188],"our":[190],"assumptions":[191],"on":[192],"under":[197],"state-aliasing":[198],"reasonable.":[200]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-09-27T00:00:00"}