{"id":"https://openalex.org/W92134822","doi":null,"title":"Hierarchical Reinforcement Learning for Communicating Agents","display_name":"Hierarchical Reinforcement Learning for Communicating Agents","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W92134822","mag":"92134822"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.4392","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.4392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www7.informatik.tu-muenchen.de/~weissg/Docs/rfw_eumas04-final.pdf","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/A5004220968","display_name":"Michael Rovatsos","orcid":"https://orcid.org/0000-0003-2517-6283","observed_orcids":["https://orcid.org/0000-0003-2517-6283"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael Rovatsos","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":"https://orcid.org/0000-0003-2517-6283","affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014224000","display_name":"Felix Fischer","orcid":"https://orcid.org/0000-0002-9724-5965","observed_orcids":["https://orcid.org/0000-0002-9724-5965"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Fischer","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":"https://orcid.org/0000-0002-9724-5965","affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112071698","display_name":"Gerhard Wei\u00df","orcid":"https://orcid.org/0000-0002-6190-2513","observed_orcids":["https://orcid.org/0000-0002-6190-2513","https://orcid.org/0000-0001-9594-7819"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Wei\u00df","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6051,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89606083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9901999831199646,"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":0.9901999831199646,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.007899999618530273,"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":0.0010000000474974513,"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/multiagent-coordination","display_name":"multi-agent coordination","score":0.871999979019165},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"case-based reasoning","score":0.949999988079071},{"id":"https://openalex.org/keywords/communication-protocols","display_name":"communication protocols","score":0.8059999942779541},{"id":"https://openalex.org/keywords/large-state-and-action-spaces","display_name":"large state and action spaces","score":0.7889999747276306}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8292232751846313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073068261146545},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6800136566162109},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5650608539581299},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5629011988639832},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5445896983146667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5183535814285278},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4317283034324646},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41660308837890625},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3629026412963867},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3448624312877655},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.32437941431999207},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09977421164512634},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08005863428115845},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.4392","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.4392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www7.informatik.tu-muenchen.de/~weissg/Docs/rfw_eumas04-final.pdf","raw_type":"text"},{"id":"mag:92134822","doi":null,"is_oa":false,"landing_page_url":"https://homepages.inf.ed.ac.uk/mrovatso/papers/rovatsosetal-eumas2004.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W331605669","https://openalex.org/W1500151553","https://openalex.org/W1500989946","https://openalex.org/W1530664320","https://openalex.org/W1564534945","https://openalex.org/W1576632330","https://openalex.org/W1592847719","https://openalex.org/W2130487245","https://openalex.org/W2312609093","https://openalex.org/W2334782222","https://openalex.org/W2400432277","https://openalex.org/W2615688110","https://openalex.org/W2782037066","https://openalex.org/W2911283634"],"related_works":["https://openalex.org/W2116399160","https://openalex.org/W7095239575","https://openalex.org/W7099987313","https://openalex.org/W331605669","https://openalex.org/W256201028","https://openalex.org/W7166709602","https://openalex.org/W2160687868","https://openalex.org/W2990927597","https://openalex.org/W2943368604","https://openalex.org/W2987204115"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"hierarchical":[3,95],"reinforcement":[4],"learning":[5],"(RL)":[6],"methods":[7,30,89],"for":[8],"communication":[9,34,69],"in":[10,36,91,105],"multiagent":[11,37],"coordination":[12],"problems":[13],"modelled":[14],"as":[15,50],"Markov":[16],"Decision":[17],"Processes":[18],"(MDPs).":[19],"To":[20],"bridge":[21],"the":[22,25,29,65,82,92],"gap":[23],"between":[24],"MDP":[26],"view":[27],"and":[28,42,101,120],"used":[31],"to":[32,72,88],"specify":[33],"protocols":[35],"systems":[38],"(using":[39],"logical":[40],"conditions":[41],"propositional":[43],"message":[44],"structure),":[45],"we":[46,63],"utilise":[47],"interaction":[48,77,83],"frames":[49,84],"powerful":[51],"policy":[52],"abstractions":[53],"that":[54,67,112],"can":[55],"be":[56],"combined":[57],"with":[58],"case-based":[59],"reasoning":[60],"techniques.":[61],"Also,":[62],"exploit":[64],"fact":[66],"breaking":[68],"processes":[70],"down":[71],"manageable":[73],"\u201cchunks":[74],"\u201d":[75],"of":[76,94,116],"sequences":[78],"(as":[79],"suggested":[80],"by":[81],"approach)":[85],"naturally":[86],"corresponds":[87],"proposed":[90],"area":[93],"RL.":[96],"The":[97],"approach":[98],"is":[99,114],"illustrated":[100],"validated":[102],"through":[103],"experiments":[104],"a":[106],"complex":[107],"application":[108],"domain":[109],"which":[110],"prove":[111],"it":[113],"capable":[115],"handling":[117],"large":[118],"state":[119],"action":[121],"spaces.":[122],"1":[123]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2016-06-24T00:00:00"}