{"id":"https://openalex.org/W4387947673","doi":"https://doi.org/10.48550/arxiv.2310.14009","title":"One is More: Diverse Perspectives within a Single Network for Efficient DRL","display_name":"One is More: Diverse Perspectives within a Single Network for Efficient DRL","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4387947673","doi":"https://doi.org/10.48550/arxiv.2310.14009"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.14009","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.14009","pdf_url":"https://arxiv.org/pdf/2310.14009","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.14009","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048928457","display_name":"Yiqin Tan","orcid":"https://orcid.org/0000-0001-7068-6341","observed_orcids":["https://orcid.org/0000-0001-7068-6341"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan, Yiqin","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090888372","display_name":"Ling Pan","orcid":"https://orcid.org/0000-0002-4413-281X","observed_orcids":["https://orcid.org/0000-0002-4413-281X"]},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pan, Ling","raw_affiliation_strings":["Mila , Universit\u00e9 de Montr\u00e9al"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila , Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082905458","display_name":"Longbo Huang","orcid":"https://orcid.org/0000-0002-7341-447X","observed_orcids":["https://orcid.org/0000-0002-7341-447X"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Longbo","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"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":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8190000057220459},{"id":"https://openalex.org/keywords/network-ensembles","display_name":"network ensembles","score":0.5139999985694885},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.875},{"id":"https://openalex.org/keywords/policy-approximation","display_name":"policy approximation","score":0.8519999980926514},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.9409999847412109},{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.9890000224113464},{"id":"https://openalex.org/keywords/mujoco","display_name":"MuJoCo","score":0.6769999861717224},{"id":"https://openalex.org/keywords/computational-cost-reduction","display_name":"computational complexity reduction","score":0.628000020980835}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8813141584396362},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.858345627784729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7520440220832825},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7330216765403748},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6873652935028076},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6866850852966309},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6489607691764832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5967299342155457},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5562877655029297},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5126992464065552},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.432700514793396},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4292517900466919},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4128953814506531},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2310.14009","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.14009","pdf_url":"https://arxiv.org/pdf/2310.14009","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-133992","doi":null,"is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-133992","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Preprint"},{"id":"doi:10.48550/arxiv.2310.14009","doi":"https://doi.org/10.48550/arxiv.2310.14009","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.14009","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.14009","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.14009","pdf_url":"https://arxiv.org/pdf/2310.14009","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387947673.pdf","grobid_xml":"https://content.openalex.org/works/W4387947673.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3024136185","https://openalex.org/W7133234894","https://openalex.org/W3204117917","https://openalex.org/W7202115536","https://openalex.org/W4417308487","https://openalex.org/W4415722160","https://openalex.org/W3209924761","https://openalex.org/W7160881114","https://openalex.org/W3010568443","https://openalex.org/W4221146424"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,82],"learning":[2,49,83],"has":[3],"achieved":[4],"remarkable":[5],"performance":[6,107],"in":[7],"various":[8,80],"domains":[9],"by":[10],"leveraging":[11],"deep":[12,81],"neural":[13,23],"networks":[14,24],"for":[15],"approximating":[16],"value":[17,27],"functions":[18,28,31],"and":[19,39,70,108],"policies.":[20],"However,":[21],"using":[22],"to":[25,79,101],"approximate":[26],"or":[29],"policy":[30],"still":[32],"faces":[33],"challenges,":[34],"including":[35,67],"low":[36],"sample":[37],"efficiency":[38],"overfitting.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"introduce":[45],"OMNet,":[46],"a":[47,55,64],"novel":[48],"paradigm":[50],"utilizing":[51],"multiple":[52],"subnetworks":[53],"within":[54],"single":[56],"network,":[57],"offering":[58],"diverse":[59],"outputs":[60],"efficiently.":[61],"We":[62],"provide":[63],"systematic":[65],"pipeline,":[66],"initialization,":[68],"training,":[69],"sampling":[71],"with":[72,85],"OMNet.":[73],"OMNet":[74],"can":[75],"be":[76],"easily":[77],"applied":[78],"algorithms":[84],"minimal":[86],"additional":[87],"overhead.":[88],"Through":[89],"comprehensive":[90],"evaluations":[91],"conducted":[92],"on":[93],"MuJoCo":[94],"benchmark,":[95],"our":[96],"findings":[97],"highlight":[98],"OMNet's":[99],"ability":[100],"strike":[102],"an":[103],"effective":[104],"balance":[105],"between":[106],"computational":[109],"cost.":[110]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2023-10-26T00:00:00"}