{"id":"https://openalex.org/W139620917","doi":null,"title":"Continuous-Time Hierarchical Reinforcement Learning","display_name":"Continuous-Time Hierarchical Reinforcement Learning","publication_year":2001,"publication_date":"2001-06-28","ids":{"openalex":"https://openalex.org/W139620917","mag":"139620917"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.28.3413","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.28.3413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.msu.edu/~mahadeva/papers/icml01.ps","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013843778","display_name":"Mohammad Ghavamzadeh","orcid":"https://orcid.org/0000-0003-0930-8688","observed_orcids":["https://orcid.org/0000-0003-0930-8688"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Ghavamzadeh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0930-8688","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061960274","display_name":"Sridhar Mahadevan","orcid":"https://orcid.org/0000-0001-6507-9109","observed_orcids":["https://orcid.org/0000-0001-6507-9109"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sridhar Mahadevan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0976,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.91835349,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"186","last_page":"193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9980000257492065},{"id":"https://openalex.org/keywords/maxq","display_name":"MAXQ","score":0.8090000152587891},{"id":"https://openalex.org/keywords/continuous-time-markov-decision-processes","display_name":"continuous-time Markov decision processes","score":0.925000011920929},{"id":"https://openalex.org/keywords/semi-markov-decision-process","display_name":"semi-Markov decision process","score":0.9769999980926514},{"id":"https://openalex.org/keywords/discounted-reward","display_name":"discounted reward","score":0.8199999928474426},{"id":"https://openalex.org/keywords/average-reward","display_name":"average reward","score":0.9940000176429749},{"id":"https://openalex.org/keywords/automated-guided-vehicles","display_name":"automated guided vehicles","score":0.8650000095367432},{"id":"https://openalex.org/keywords/policy-learning","display_name":"policy learning","score":0.6269999742507935}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7573271989822388},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6674929857254028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4639299511909485},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3409305810928345}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.28.3413","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.28.3413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.msu.edu/~mahadeva/papers/icml01.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.91.8279","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.91.8279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ualberta.ca/~mgh/PUBLICATIONS/icml01.pdf","raw_type":"text"},{"id":"mag:139620917","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/icml/icml2001.html#GhavamzadehM01","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W165707239","https://openalex.org/W256201028","https://openalex.org/W1549353711","https://openalex.org/W1568042657","https://openalex.org/W2095770075","https://openalex.org/W2101915445","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2153947321","https://openalex.org/W2334782222"],"related_works":["https://openalex.org/W325315585","https://openalex.org/W1218520990","https://openalex.org/W256362207","https://openalex.org/W1936091723","https://openalex.org/W1982678075","https://openalex.org/W2143496582","https://openalex.org/W7099387294","https://openalex.org/W7096132658","https://openalex.org/W2375852414","https://openalex.org/W1488730473"],"abstract_inverted_index":{"Hierarchical":[0],"reinforcement":[1,67],"learning":[2,22,68],"(RL)":[3],"is":[4],"a":[5,84],"general":[6],"framework":[7],"which":[8],"studies":[9],"how":[10],"to":[11,19,39,55,83],"exploit":[12],"the":[13,33,40,52],"structure":[14],"of":[15],"actions":[16],"and":[17,58,74,90,94],"tasks":[18],"accelerate":[20],"policy":[21],"in":[23,28],"large":[24],"domains.":[25],"Prior":[26],"work":[27],"hierarchical":[29,66],"RL,":[30],"such":[31],"as":[32,99,101],"MAXQ":[34,53,73],"method,":[35],"has":[36],"been":[37],"limited":[38],"discrete-time":[41],"discounted":[42,57,71],"reward":[43,60,72,77],"semi-Markov":[44],"decision":[45],"process":[46],"(SMDP)":[47],"model.":[48],"This":[49],"paper":[50],"generalizes":[51],"method":[54],"continuous-time":[56,70,75],"average":[59,76],"SMDP":[61],"models.":[62],"We":[63,79],"describe":[64],"two":[65],"algorithms:":[69],"MAXQ.":[78],"apply":[80],"these":[81],"algorithms":[82],"complex":[85],"multiagent":[86],"AGV":[87,104],"scheduling":[88,105],"problem,":[89],"compare":[91],"their":[92],"performance":[93],"speed":[95],"with":[96],"each":[97],"other,":[98],"well":[100],"several":[102],"well-known":[103],"heuristics.":[106],"1.":[107]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}