{"id":"https://openalex.org/W4415080562","doi":"https://doi.org/10.48550/arxiv.2502.21186","title":"Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction","display_name":"Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction","publication_year":2025,"publication_date":"2025-02-28","ids":{"openalex":"https://openalex.org/W4415080562","doi":"https://doi.org/10.48550/arxiv.2502.21186"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.21186","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.21186","pdf_url":"https://arxiv.org/pdf/2502.21186","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.21186","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055677035","display_name":"Baiting Luo","orcid":"https://orcid.org/0009-0008-5830-2542"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Luo, Baiting","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113092496","display_name":"Ava Pettet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pettet, Ava","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049435924","display_name":"\u00c1ron L\u00e1szka","orcid":"https://orcid.org/0000-0001-7400-2357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laszka, Aron","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049776939","display_name":"Abhishek Dubey","orcid":"https://orcid.org/0000-0002-0168-4948"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dubey, Abhishek","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5040206778","display_name":"Ayan Mukhopadhyay","orcid":"https://orcid.org/0000-0002-8877-2165"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mukhopadhyay, Ayan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055677035"],"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.7049000263214111,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.7049000263214111,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11106","display_name":"Data Management and Algorithms","score":0.6367999911308289,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.631600022315979,"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/scalability","display_name":"Scalability","score":0.492000013589859},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.47189998626708984},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.43479999899864197},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.38499999046325684},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.38029998540878296},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.37389999628067017},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.367000013589859},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3580000102519989},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.35040000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7468000054359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5602999925613403},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5446000099182129},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.47189998626708984},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.43479999899864197},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.37389999628067017},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.367000013589859},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.35040000081062317},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.336899995803833},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.3127000033855438},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C127491075","wikidata":"https://www.wikidata.org/wiki/Q7617825","display_name":"Stochastic modelling","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.21186","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.21186","pdf_url":"https://arxiv.org/pdf/2502.21186","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2502.21186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.21186","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.21186","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.21186","pdf_url":"https://arxiv.org/pdf/2502.21186","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sequential":[0],"decision-making":[1],"in":[2,8,19,102,188,190],"high-dimensional":[3,163,196],"continuous":[4,123,156],"action":[5,72,149,197],"spaces,":[6],"particularly":[7],"stochastic":[9,40,122,160,193],"environments,":[10],"faces":[11],"significant":[12],"computational":[13],"challenges.":[14],"We":[15,43],"explore":[16],"this":[17,52],"challenge":[18,53],"the":[20,104,107,182,185],"traditional":[21],"offline":[22,118],"RL":[23,119],"setting,":[24],"where":[25],"an":[26],"agent":[27],"must":[28],"learn":[29],"how":[30],"to":[31,133,162],"make":[32],"decisions":[33],"based":[34],"on":[35],"data":[36],"collected":[37],"through":[38,62],"a":[39,56,63,76,84],"behavior":[41,108],"policy.":[42],"present":[44],"Latent":[45],"Macro":[46],"Action":[47],"Planner":[48],"(L-MAP),":[49],"which":[50],"addresses":[51],"by":[54,110],"learning":[55],"set":[57],"of":[58,92,184],"temporally":[59],"extended":[60],"macro-actions":[61],"state-conditional":[64],"Vector":[65],"Quantized":[66],"Variational":[67],"Autoencoder":[68],"(VQ-VAE),":[69],"effectively":[70],"reducing":[71],"dimensionality.":[73,150],"L-MAP":[74,126,142,167],"employs":[75],"(separate)":[77],"learned":[78],"prior":[79],"model":[80,87],"that":[81,141],"acts":[82],"as":[83],"latent":[85,131],"transition":[86],"and":[88,106,173,192],"allows":[89],"efficient":[90],"sampling":[91],"plausible":[93],"actions.":[94],"During":[95],"planning,":[96],"our":[97],"approach":[98,187],"accounts":[99],"for":[100],"stochasticity":[101],"both":[103],"environment":[105],"policy":[109],"using":[111],"Monte":[112],"Carlo":[113],"tree":[114],"search":[115],"(MCTS).":[116],"In":[117],"settings,":[120],"including":[121],"control":[124,157],"tasks,":[125],"efficiently":[127],"searches":[128],"over":[129],"discrete":[130],"actions":[132],"yield":[134],"high":[135],"expected":[136],"returns.":[137],"Empirical":[138],"results":[139],"demonstrate":[140],"maintains":[143],"low":[144],"decision":[145],"latency":[146],"despite":[147],"increased":[148],"Notably,":[151],"across":[152],"tasks":[153],"ranging":[154],"from":[155],"with":[158,176,195],"inherently":[159],"dynamics":[161],"robotic":[164],"hand":[165],"manipulation,":[166],"significantly":[168],"outperforms":[169],"existing":[170],"model-based":[171],"methods":[172],"performs":[174],"on-par":[175],"strong":[177],"model-free":[178],"actor-critic":[179],"baselines,":[180],"highlighting":[181],"effectiveness":[183],"proposed":[186],"planning":[189],"complex":[191],"environments":[194],"spaces.":[198]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-12T00:00:00"}