{"id":"https://openalex.org/W4400433949","doi":"https://doi.org/10.48550/arxiv.2407.03674","title":"Short-Long Policy Evaluation with Novel Actions","display_name":"Short-Long Policy Evaluation with Novel Actions","publication_year":2024,"publication_date":"2024-07-04","ids":{"openalex":"https://openalex.org/W4400433949","doi":"https://doi.org/10.48550/arxiv.2407.03674"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2407.03674","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.03674","pdf_url":"https://arxiv.org/pdf/2407.03674","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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.03674","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075990123","display_name":"Hyunji Nam","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nam, Hyunji Alex","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094066203","display_name":"Yash Chandak","orcid":"https://orcid.org/0000-0002-6276-5549","observed_orcids":["https://orcid.org/0000-0002-6276-5549"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandak, Yash","raw_affiliation_strings":["Department of Computer Science Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084989076","display_name":"Emma Brunskill","orcid":"https://orcid.org/0000-0002-3971-7127","observed_orcids":["https://orcid.org/0000-0002-3971-7127"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brunskill, Emma","raw_affiliation_strings":["Department of Computer Science Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"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":true,"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":0.5145999789237976,"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":0.5145999789237976,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.43869999051094055,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.012600000016391277,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sequential-decision-making","display_name":"sequential decision making","score":0.8980000019073486},{"id":"https://openalex.org/keywords/long-term-outcomes","display_name":"long-term outcomes","score":0.7160000205039978},{"id":"https://openalex.org/keywords/hiv-treatment","display_name":"HIV treatment","score":0.5680000185966492},{"id":"https://openalex.org/keywords/dialysis","display_name":"dialysis","score":0.9980000257492065},{"id":"https://openalex.org/keywords/battery-charging","display_name":"battery charging","score":0.9919999837875366},{"id":"https://openalex.org/keywords/ai-safety","display_name":"AI safety","score":0.9480000138282776}],"concepts":[{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.40024539828300476}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2407.03674","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.03674","pdf_url":"https://arxiv.org/pdf/2407.03674","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.03674","doi":"https://doi.org/10.48550/arxiv.2407.03674","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.03674","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.03674","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.03674","pdf_url":"https://arxiv.org/pdf/2407.03674","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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400433949.pdf","grobid_xml":"https://content.openalex.org/works/W4400433949.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2135721773","https://openalex.org/W2155183960","https://openalex.org/W2166944917","https://openalex.org/W2273088453","https://openalex.org/W2804152667","https://openalex.org/W2924382816","https://openalex.org/W3026178382","https://openalex.org/W3110395132","https://openalex.org/W3133591098","https://openalex.org/W3206432993","https://openalex.org/W4290927958","https://openalex.org/W4306705424","https://openalex.org/W4388926361"],"related_works":["https://openalex.org/W4405956680","https://openalex.org/W4417116219","https://openalex.org/W4396759029","https://openalex.org/W2596886064","https://openalex.org/W7138948018","https://openalex.org/W7214894101","https://openalex.org/W7160916093","https://openalex.org/W7160182835","https://openalex.org/W2771401938","https://openalex.org/W6910510183"],"abstract_inverted_index":{"From":[0],"incorporating":[1],"LLMs":[2],"in":[3,20,34,144],"education,":[4],"to":[5,12,45,82,157],"identifying":[6,149],"new":[7,18,56,71,105,152],"drugs":[8],"and":[9,29,89,130],"improving":[10],"ways":[11],"charge":[13],"batteries,":[14],"innovators":[15],"constantly":[16],"try":[17],"strategies":[19],"search":[21],"of":[22,41,50,69,97,125],"better":[23],"long-term":[24,67,76],"outcomes":[25,68],"for":[26,107,111,142],"students,":[27],"patients":[28],"consumers.":[30],"One":[31],"major":[32],"bottleneck":[33],"this":[35],"innovation":[36],"cycle":[37],"is":[38,61,155],"the":[39,47,94],"amount":[40],"time":[42],"it":[43],"takes":[44],"observe":[46],"downstream":[48],"effects":[49],"a":[51,70,104,151],"decision":[52,72,87,113,153],"policy":[53,73,109,154],"that":[54,136],"incorporates":[55],"interventions.":[57],"The":[58],"key":[59],"question":[60],"whether":[62],"we":[63,102],"can":[64,139],"quickly":[65,148],"evaluate":[66],"without":[74],"making":[75,114],"observations.":[77],"Organizations":[78],"often":[79],"have":[80,158],"access":[81],"prior":[83,121],"data":[84],"about":[85],"past":[86,163],"policies":[88],"their":[90],"outcomes,":[91],"evaluated":[92],"over":[93],"full":[95],"horizon":[96],"interest.":[98],"Motivated":[99],"by":[100,147],"this,":[101],"introduce":[103],"setting":[106],"short-long":[108],"evaluation":[110],"sequential":[112],"tasks.":[115],"Our":[116],"proposed":[117],"methods":[118,138],"significantly":[119],"outperform":[120],"results":[122],"on":[123],"simulators":[124],"HIV":[126],"treatment,":[127],"kidney":[128],"dialysis":[129],"battery":[131],"charging.":[132],"We":[133],"also":[134],"demonstrate":[135],"our":[137],"be":[140],"useful":[141],"applications":[143],"AI":[145],"safety":[146],"when":[150],"likely":[156],"substantially":[159],"lower":[160],"performance":[161],"than":[162],"policies.":[164]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-07-09T00:00:00"}
