{"id":"https://openalex.org/W4362598622","doi":"https://doi.org/10.48550/arxiv.2304.00776","title":"Chain-of-Thought Predictive Control","display_name":"Chain-of-Thought Predictive Control","publication_year":2023,"publication_date":"2023-04-03","ids":{"openalex":"https://openalex.org/W4362598622","doi":"https://doi.org/10.48550/arxiv.2304.00776"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2304.00776","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.00776","pdf_url":"https://arxiv.org/pdf/2304.00776","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.00776","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032003934","display_name":"Zhiwei Jia","orcid":"https://orcid.org/0000-0002-8619-4787"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jia, Zhiwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090032330","display_name":"Vineet Thumuluri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thumuluri, Vineet","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075643825","display_name":"Fangchen Liu","orcid":"https://orcid.org/0000-0002-8987-6396"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Fangchen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001151596","display_name":"Linghao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Linghao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114056394","display_name":"Zhiao Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Zhiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004663761","display_name":"Hao Su","orcid":"https://orcid.org/0000-0002-0178-6610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Hao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5032003934"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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":0.9765999913215637,"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":0.9765999913215637,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.972000002861023,"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/computer-science","display_name":"Computer science","score":0.8124736547470093},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.7418683171272278},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.7073922157287598},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6912150382995605},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6225888729095459},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5679864287376404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5654093623161316},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47947534918785095},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47571972012519836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8124736547470093},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.7418683171272278},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7073922157287598},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6912150382995605},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6225888729095459},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5679864287376404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5654093623161316},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47947534918785095},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47571972012519836},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2304.00776","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.00776","pdf_url":"https://arxiv.org/pdf/2304.00776","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2304.00776","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2304.00776","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.00776","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.00776","pdf_url":"https://arxiv.org/pdf/2304.00776","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4362598622.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W3034924094"],"abstract_inverted_index":{"We":[0,15,100],"study":[1],"generalizable":[2,131],"policy":[3,132],"learning":[4,21],"from":[5],"demonstrations":[6],"for":[7,72,130],"complex":[8],"low-level":[9],"control":[10],"(e.g.,":[11],"contact-rich":[12],"object":[13],"manipulations).":[14],"propose":[16,29,85],"a":[17,67,86,111],"novel":[18],"hierarchical":[19],"imitation":[20],"method":[22],"that":[23,34,89],"utilizes":[24],"sub-optimal":[25,150],"demos.":[26,151],"Firstly,":[27],"we":[28,76,84],"an":[30,45],"observation":[31],"space-agnostic":[32],"approach":[33],"efficiently":[35],"discovers":[36],"the":[37,42,60,63,73,80,94,97,128],"multi-step":[38],"subskill":[39,104],"decomposition":[40],"of":[41,69,127],"demos":[43],"in":[44],"unsupervised":[46],"manner.":[47],"By":[48],"grouping":[49],"temporarily":[50],"close":[51],"and":[52,103,110,123],"functionally":[53],"similar":[54],"actions":[55],"into":[56],"subskill-level":[57,98],"demo":[58],"segments,":[59],"observations":[61],"at":[62,120],"segment":[64],"boundaries":[65],"constitute":[66],"chain":[68],"planning":[70],"steps":[71],"task,":[74],"which":[75,115],"refer":[77],"to":[78,92],"as":[79,96],"chain-of-thought":[81],"(CoT).":[82],"Next,":[83],"Transformer-based":[87],"design":[88],"effectively":[90],"learns":[91],"predict":[93],"CoT":[95],"guidance.":[99],"couple":[101],"action":[102],"predictions":[105],"via":[106],"learnable":[107],"prompt":[108],"tokens":[109],"hybrid":[112],"masking":[113],"strategy,":[114],"enable":[116],"dynamically":[117],"updated":[118],"guidance":[119],"test":[121],"time":[122],"improve":[124],"feature":[125],"representation":[126],"trajectory":[129],"learning.":[133],"Our":[134],"method,":[135],"Chain-of-Thought":[136],"Predictive":[137],"Control":[138],"(CoTPC),":[139],"consistently":[140],"surpasses":[141],"existing":[142],"strong":[143],"baselines":[144],"on":[145],"challenging":[146],"manipulation":[147],"tasks":[148],"with":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}