{"id":"https://openalex.org/W7056863049","doi":null,"title":"Hierarchical Reinforcement Learning for Spatio-temporal Planning","display_name":"Hierarchical Reinforcement Learning for Spatio-temporal Planning","publication_year":2018,"publication_date":"2018-09-28","ids":{"openalex":"https://openalex.org/W7056863049"},"language":"en","primary_location":{"id":"pmh:oai:tudelft.nl:uuid:5b24c89d-0f5c-40e0-86a6-dd453250860d","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:5b24c89d-0f5c-40e0-86a6-dd453250860d","pdf_url":"http://resolver.tudelft.nl/uuid:5b24c89d-0f5c-40e0-86a6-dd453250860d","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://resolver.tudelft.nl/uuid:5b24c89d-0f5c-40e0-86a6-dd453250860d","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012590059","display_name":"Shambhuraj Sawant","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sawant, Shambhuraj (author)","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5012590059"],"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":true,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9961000084877014,"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":0.9961000084877014,"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":0.003800000064074993,"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":0.0,"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/hierarchical-reinforcement-learning","display_name":"hierarchical reinforcement learning","score":1.0},{"id":"https://openalex.org/keywords/semi-markov-decision-process","display_name":"semi-Markov decision process","score":0.8650000095367432},{"id":"https://openalex.org/keywords/factored-markov-decision-processes","display_name":"factored Markov decision processes","score":0.9139999747276306},{"id":"https://openalex.org/keywords/dynamic-bayesian-networks","display_name":"dynamic Bayesian networks","score":0.9039999842643738},{"id":"https://openalex.org/keywords/state-abstraction","display_name":"state abstraction","score":0.7310000061988831},{"id":"https://openalex.org/keywords/temporal-abstraction","display_name":"temporal abstraction","score":0.9879999756813049},{"id":"https://openalex.org/keywords/goal-directed-planning","display_name":"goal-oriented planning","score":0.8759999871253967},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"curse of dimensionality","score":0.8939999938011169},{"id":"https://openalex.org/keywords/causal-structure","display_name":"causal structure","score":0.48899999260902405}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8317999839782715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6881999969482422},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6629999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6273999810218811},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5600000023841858},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5461999773979187},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41769999265670776},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.37439998984336853},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.36390000581741333},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.336899995803833},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C124527596","wikidata":"https://www.wikidata.org/wiki/Q17029359","display_name":"Hierarchical control system","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C130327152","wikidata":"https://www.wikidata.org/wiki/Q748349","display_name":"Mathematical structure","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C50292564","wikidata":"https://www.wikidata.org/wiki/Q2462783","display_name":"Computational learning theory","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:tudelft.nl:uuid:5b24c89d-0f5c-40e0-86a6-dd453250860d","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:5b24c89d-0f5c-40e0-86a6-dd453250860d","pdf_url":"http://resolver.tudelft.nl/uuid:5b24c89d-0f5c-40e0-86a6-dd453250860d","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:5b24c89d-0f5c-40e0-86a6-dd453250860d","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:5b24c89d-0f5c-40e0-86a6-dd453250860d","pdf_url":"http://resolver.tudelft.nl/uuid:5b24c89d-0f5c-40e0-86a6-dd453250860d","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7056863049.pdf","grobid_xml":"https://content.openalex.org/works/W7056863049.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2372300130","https://openalex.org/W4253921394","https://openalex.org/W4235743572","https://openalex.org/W7204525962","https://openalex.org/W7097757008","https://openalex.org/W2306711933","https://openalex.org/W2296209277","https://openalex.org/W4392445223","https://openalex.org/W2277639078","https://openalex.org/W7100860439"],"abstract_inverted_index":{"Reinforcement":[0,111],"learning":[1,12,137],"(RL)":[2],"is":[3,147],"an":[4,20,76],"area":[5],"of":[6,36,92,141,159,166,190],"Machine":[7],"Learning":[8,50,112],"(ML)":[9],"concerned":[10],"with":[11,44,163],"how":[13],"a":[14,101,142,188,195],"software-defined":[15],"agent":[16],"should":[17],"act":[18],"in":[19,41,47,54,69,149,182,198],"environment":[21],"to":[22,27,99,116,204,219],"maximize":[23],"the":[24,34,38,45,51,59,70,73,104,119,150,156,160,164,177,183,200,214],"rewards.":[25],"Similar":[26],"many":[28],"ML":[29],"methods,":[30],"RL":[31],"suffers":[32],"from":[33],"curse":[35],"dimensionality,":[37],"exponential":[39],"increase":[40,46],"solution":[42,102],"space":[43],"problem":[48,121,161,184,201],"dimensions.":[49],"hierarchy":[52,189],"present":[53],"underlying":[55],"problems,":[56],"formulated":[57],"using":[58,192],"Markov":[60],"Decision":[61],"Processes":[62],"(MDPs)":[63],"framework,":[64],"may":[65],"exploit":[66],"inherent":[67],"structure":[68,140,158],"environment.":[71],"Using":[72],"hierarchical":[74,139],"structure,":[75],"MDP":[77],"can":[78,95],"be":[79,97,205],"divided":[80],"into":[81,122,154],"several":[82,126],"simpler":[83],"semi-MDPs":[84],"(SMDPs)":[85],"having":[86],"temporally":[87],"extended":[88],"actions.":[89],"The":[90,107,172],"solutions":[91],"smaller":[93],"SMDPs":[94,123,191],"then":[96],"re-combined":[98],"form":[100],"for":[103,109,128,136,207],"original":[105,120],"MDP.":[106],"methods":[108],"Hierarchical":[110],"(HRL)":[113],"explore":[114],"ways":[115],"break":[117],"down":[118],"while":[124],"providing":[125],"opportunities":[127],"state":[129,178,202],"and":[130,179,186],"temporal":[131,180],"abstractions.":[132],"A":[133],"novel":[134],"algorithm":[135],"this":[138],"discrete-state":[143],"goal-oriented":[144],"Factored-MDP":[145],"(FMDP)":[146],"proposed":[148,173],"thesis":[151],"work":[152],"taking":[153],"account":[155],"causal":[157],"domain":[162,185],"use":[165],"Dynamic":[167],"Bayesian":[168],"Network":[169],"(DBN)":[170],"model.":[171],"method":[174],"autonomously":[175],"learns":[176],"abstractions":[181],"constructs":[187],"them.":[193],"Such":[194],"decomposition":[196],"results":[197],"decreasing":[199],"dimensions":[203],"considered":[206],"solving":[208],"each":[209],"SMDP":[210],"and,":[211],"hence,":[212],"reducing":[213],"computational":[215],"complexity":[216],"induced":[217],"due":[218],"increased":[220],"dimensionality.":[221]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}