{"id":"https://openalex.org/W2998802444","doi":"https://doi.org/10.48550/arxiv.2001.02652","title":"Sample-based Distributional Policy Gradient","display_name":"Sample-based Distributional Policy Gradient","publication_year":2020,"publication_date":"2020-01-08","ids":{"openalex":"https://openalex.org/W2998802444","doi":"https://doi.org/10.48550/arxiv.2001.02652","mag":"2998802444"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2001.02652","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.02652","pdf_url":"https://arxiv.org/pdf/2001.02652","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.02652","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Singh, Rahul","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Singh, Rahul","raw_affiliation_strings":["Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046628126","display_name":"Keuntaek Lee","orcid":"https://orcid.org/0000-0001-5955-5965","observed_orcids":["https://orcid.org/0000-0001-5955-5965"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lee, Keuntaek","raw_affiliation_strings":["Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066940107","display_name":"Yongxin Chen","orcid":"https://orcid.org/0000-0002-1459-6365","observed_orcids":["https://orcid.org/0000-0002-1459-6365"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Yongxin","raw_affiliation_strings":["Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":13,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/distributional-reinforcement-learning","display_name":"distributional reinforcement learning","score":0.9760000109672546},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.5600000023841858},{"id":"https://openalex.org/keywords/reparameterization","display_name":"reparameterization","score":0.75},{"id":"https://openalex.org/keywords/continuous-action-spaces","display_name":"continuous action spaces","score":0.7089999914169312},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.6800000071525574},{"id":"https://openalex.org/keywords/robot-control","display_name":"robot control","score":0.7319999933242798}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8550248742103577},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.672184407711029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6247797012329102},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.565027117729187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5501521229743958},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5271068811416626},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5238630771636963},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.43291985988616943},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.41920045018196106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40793377161026},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24940583109855652},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1046648621559143},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2001.02652","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.02652","pdf_url":"https://arxiv.org/pdf/2001.02652","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":"doi:10.48550/arxiv.2001.02652","doi":"https://doi.org/10.48550/arxiv.2001.02652","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.02652","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:2001.02652","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.02652","pdf_url":"https://arxiv.org/pdf/2001.02652","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2998802444.pdf","grobid_xml":"https://content.openalex.org/works/W2998802444.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1585160083","https://openalex.org/W1959608418","https://openalex.org/W2046033161","https://openalex.org/W2099471712","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2341171179","https://openalex.org/W2739748921","https://openalex.org/W2781585732","https://openalex.org/W2787613197","https://openalex.org/W2793477525","https://openalex.org/W2794558616","https://openalex.org/W2798705390","https://openalex.org/W2803308811","https://openalex.org/W2885797512","https://openalex.org/W2949980113","https://openalex.org/W2951004968","https://openalex.org/W2963388106","https://openalex.org/W2963423916","https://openalex.org/W2963438131","https://openalex.org/W2963757175","https://openalex.org/W2964161785","https://openalex.org/W3002189898","https://openalex.org/W3010042009","https://openalex.org/W3037207827","https://openalex.org/W3139377883","https://openalex.org/W4297782457"],"related_works":["https://openalex.org/W4395661371","https://openalex.org/W2798705390","https://openalex.org/W4401417037","https://openalex.org/W3101441984","https://openalex.org/W3177063094","https://openalex.org/W6948576674","https://openalex.org/W2917022709","https://openalex.org/W4402854595","https://openalex.org/W4225605135","https://openalex.org/W4281779625"],"abstract_inverted_index":{"Distributional":[0],"reinforcement":[1,7],"learning":[2,8],"(DRL)":[3],"is":[4],"a":[5,92],"recent":[6],"framework":[9],"whose":[10],"success":[11],"has":[12,120],"been":[13],"supported":[14],"by":[15,66],"various":[16],"empirical":[17],"studies.":[18],"It":[19,84],"relies":[20],"on":[21,49,52],"the":[22,27,31,36,40,46,86,106],"key":[23],"idea":[24],"of":[25,39,45],"replacing":[26],"expected":[28],"return":[29,32,87],"with":[30,54,70,105],"distribution,":[33],"which":[34,119],"captures":[35],"intrinsic":[37],"randomness":[38],"long":[41],"term":[42],"rewards.":[43],"Most":[44],"existing":[47],"literature":[48],"DRL":[50],"focuses":[51],"problems":[53],"discrete":[55],"action":[56,72],"space":[57,73],"and":[58,100,127,134],"value":[59],"based":[60],"methods.":[61],"In":[62],"this":[63],"work,":[64],"motivated":[65],"applications":[67],"in":[68,97,111],"robotics":[69],"continuous":[71],"control":[74],"settings,":[75],"we":[76],"propose":[77],"sample-based":[78],"distributional":[79,114],"policy":[80,108,116],"gradient":[81,109],"(SDPG)":[82],"algorithm.":[83],"models":[85],"distribution":[88],"using":[89],"samples":[90],"via":[91],"reparameterization":[93],"technique":[94],"widely":[95],"used":[96],"generative":[98],"modeling":[99],"inference.":[101],"We":[102,124],"compare":[103],"SDPG":[104,126],"state-of-art":[107,122],"method":[110],"DRL,":[112],"distributed":[113],"deterministic":[115],"gradients":[117],"(D4PG),":[118],"demonstrated":[121],"performance.":[123],"apply":[125],"D4PG":[128],"to":[129],"multiple":[130],"OpenAI":[131],"Gym":[132],"environments":[133],"observe":[135],"that":[136],"our":[137],"algorithm":[138],"shows":[139],"better":[140],"sample":[141],"efficiency":[142],"as":[143,145],"well":[144],"higher":[146],"reward":[147],"for":[148],"most":[149],"tasks.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2020-01-23T00:00:00"}