{"id":"https://openalex.org/W4383109304","doi":"https://doi.org/10.1109/icra48891.2023.10161186","title":"Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policy Optimization","display_name":"Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policy Optimization","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383109304","doi":"https://doi.org/10.1109/icra48891.2023.10161186"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5052013511","display_name":"Souradip Chakraborty","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Souradip Chakraborty","raw_affiliation_strings":["University of Maryland,College Park,MD,USA","University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039563144","display_name":"Amrit Singh Bedi","orcid":"https://orcid.org/0000-0002-8807-2695"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amrit Singh Bedi","raw_affiliation_strings":["University of Maryland,College Park,MD,USA","University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080472165","display_name":"Kasun Weerakoon","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kasun Weerakoon","raw_affiliation_strings":["University of Maryland,College Park,MD,USA","University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083140373","display_name":"Prithvi Poddar","orcid":"https://orcid.org/0000-0003-1172-8294"},"institutions":[{"id":"https://openalex.org/I181996519","display_name":"Indian Institute of Science Education and Research Pune","ror":"https://ror.org/028qa3n13","country_code":"IN","type":"education","lineage":["https://openalex.org/I181996519"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prithvi Poddar","raw_affiliation_strings":["Indian Institutes of Science Education and Research"],"affiliations":[{"raw_affiliation_string":"Indian Institutes of Science Education and Research","institution_ids":["https://openalex.org/I181996519"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025896653","display_name":"Alec Koppel","orcid":"https://orcid.org/0000-0003-2447-2873"},"institutions":[{"id":"https://openalex.org/I1305429384","display_name":"JPMorgan Chase & Co (United States)","ror":"https://ror.org/01x3kkr08","country_code":"US","type":"company","lineage":["https://openalex.org/I1305429384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alec Koppel","raw_affiliation_strings":["JP Morgan AI Research,NewYork,NY,USA","JP Morgan AI Research, NewYork, NY, USA"],"affiliations":[{"raw_affiliation_string":"JP Morgan AI Research,NewYork,NY,USA","institution_ids":["https://openalex.org/I1305429384"]},{"raw_affiliation_string":"JP Morgan AI Research, NewYork, NY, USA","institution_ids":["https://openalex.org/I1305429384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086188394","display_name":"Pratap Tokekar","orcid":"https://orcid.org/0000-0002-3715-0382"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pratap Tokekar","raw_affiliation_strings":["University of Maryland,College Park,MD,USA","University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland,College Park,MD,USA","University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5052013511"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":0.5254,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70471151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"989","last_page":"995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12288","display_name":"Optimization and Search Problems","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9878000020980835,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7307698726654053},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6844232678413391},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6037381291389465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5860671401023865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5833102464675903},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.49761417508125305},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4727029800415039},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4527466893196106},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.44303321838378906},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3292495608329773},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19641825556755066}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7307698726654053},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6844232678413391},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6037381291389465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5860671401023865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5833102464675903},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.49761417508125305},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4727029800415039},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4527466893196106},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.44303321838378906},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3292495608329773},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19641825556755066},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1481900550","https://openalex.org/W1522301498","https://openalex.org/W1548439805","https://openalex.org/W1771410628","https://openalex.org/W2000042664","https://openalex.org/W2098774185","https://openalex.org/W2144446635","https://openalex.org/W2148112459","https://openalex.org/W2198041288","https://openalex.org/W2417786368","https://openalex.org/W2604382266","https://openalex.org/W2623491082","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2788862220","https://openalex.org/W2803616302","https://openalex.org/W2938421504","https://openalex.org/W2963099939","https://openalex.org/W2963277051","https://openalex.org/W2963411833","https://openalex.org/W2963523627","https://openalex.org/W2964319688","https://openalex.org/W2964631455","https://openalex.org/W2970623506","https://openalex.org/W2989598077","https://openalex.org/W2999862950","https://openalex.org/W3006355000","https://openalex.org/W3009440920","https://openalex.org/W3018897351","https://openalex.org/W3024652448","https://openalex.org/W3109546547","https://openalex.org/W3122232370","https://openalex.org/W3130717831","https://openalex.org/W3131482536","https://openalex.org/W3158799570","https://openalex.org/W3204691825","https://openalex.org/W3216283008","https://openalex.org/W4214717370","https://openalex.org/W4221157325","https://openalex.org/W4221160486","https://openalex.org/W4249775755","https://openalex.org/W4285044830","https://openalex.org/W4287119221","https://openalex.org/W4287726354","https://openalex.org/W4289760659","https://openalex.org/W4318751317","https://openalex.org/W4382239208","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6674884181","https://openalex.org/W6716474083","https://openalex.org/W6718092244","https://openalex.org/W6739193204","https://openalex.org/W6741002519","https://openalex.org/W6742461812","https://openalex.org/W6744563498","https://openalex.org/W6751285671","https://openalex.org/W6751972096","https://openalex.org/W6763249885","https://openalex.org/W6769045504","https://openalex.org/W6770407973","https://openalex.org/W6773935107","https://openalex.org/W6774781930","https://openalex.org/W6776743287","https://openalex.org/W6776824048","https://openalex.org/W6779907882","https://openalex.org/W6780559895","https://openalex.org/W6797142581","https://openalex.org/W6809322615","https://openalex.org/W6810137820","https://openalex.org/W6839015296"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,83,89,99,176,187],"novel":[6],"Heavy-Tailed":[7],"Stochastic":[8],"Policy":[9],"Gradient":[10],"(HT-PSG)":[11],"algorithm":[12,108],"to":[13,46,97,113,169,191],"deal":[14],"with":[15,88,129],"the":[16,41,47,54,66,104,118],"challenges":[17],"of":[18,50,120,126,161],"sparse":[19,67,130],"rewards":[20,26,131],"in":[21,29,103,141,159],"continuous":[22,30,127],"control":[23,31,128],"problems.":[24],"Sparse":[25,139,145],"are":[27],"common":[28],"robotics":[32],"tasks":[33,125,158],"such":[34,132],"as":[35,133],"manipulation":[36],"and":[37,39,77,144],"navigation":[38,177,194],"make":[40],"learning":[42],"problem":[43],"hard":[44],"due":[45],"non-trivial":[48],"estimation":[49],"value":[51],"functions":[52],"over":[53],"state":[55],"space.":[56],"This":[57],"demands":[58],"either":[59],"reward":[60,68,165],"shaping":[61],"or":[62],"expert":[63,114,170],"demonstrations":[64,73],"for":[65],"environment.":[69],"However,":[70],"obtaining":[71],"high-quality":[72],"is":[74],"quite":[75],"expensive":[76],"sometimes":[78],"even":[79],"impossible.":[80],"We":[81,116,151,172],"propose":[82],"heavy-tailed":[84],"policy":[85,92,178],"parametrization":[86],"along":[87],"modified":[90],"momentum-based":[91],"gradient":[93],"tracking":[94],"scheme":[95],"(HT-SPG)":[96],"induce":[98],"stable":[100],"exploratory":[101],"behavior":[102],"algorithm.":[105],"The":[106],"proposed":[107],"does":[109],"not":[110],"require":[111],"access":[112,168],"demonstrations.":[115,171],"test":[117],"performance":[119,154],"HT-SPG":[121,181],"on":[122],"various":[123],"benchmark":[124],"1D":[134],"Mario,":[135],"Pathological":[136],"Mountain":[137],"Car,":[138],"Pendulum":[140],"OpenAI":[142],"Gym,":[143],"MuJoCo":[146],"environments":[147],"(Hopper-v2,":[148],"Half-Cheetah,":[149],"Walker-2D).":[150],"show":[152],"consistent":[153],"improvement":[155],"across":[156],"all":[157],"terms":[160],"high":[162],"average":[163],"cumulative":[164],"without":[166],"requiring":[167],"further":[173],"demonstrate":[174],"that":[175],"trained":[179],"using":[180],"can":[182],"be":[183],"easily":[184],"transferred":[185],"into":[186],"Clearpath":[188],"Husky":[189],"robot":[190],"perform":[192],"real-world":[193],"tasks.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-01T00:03:43.161839","created_date":"2025-10-10T00:00:00"}