{"id":"https://openalex.org/W2976792479","doi":"https://doi.org/10.1109/ssrr.2019.8848957","title":"Sample Efficient Reinforcement Learning for Navigation in Complex Environments","display_name":"Sample Efficient Reinforcement Learning for Navigation in Complex Environments","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2976792479","doi":"https://doi.org/10.1109/ssrr.2019.8848957","mag":"2976792479"},"language":"en","primary_location":{"id":"doi:10.1109/ssrr.2019.8848957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssrr.2019.8848957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","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/A5028230181","display_name":"Barzin Moridian","orcid":"https://orcid.org/0000-0001-7806-9284"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Barzin Moridian","raw_affiliation_strings":["Mechanical Engineering, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Mechanical Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040767950","display_name":"Brian R. Page","orcid":"https://orcid.org/0000-0002-3634-8944"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian R. Page","raw_affiliation_strings":["Mechanical Engineering, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Mechanical Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063519076","display_name":"Nina Mahmoudian","orcid":"https://orcid.org/0000-0002-3285-8234"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nina Mahmoudian","raw_affiliation_strings":["Mechanical Engineering, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Mechanical Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028230181"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.2024,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5421452,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8278442621231079},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7778509259223938},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.7158783078193665},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.6444360017776489},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6185650825500488},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5850902795791626},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5675897598266602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5351091027259827},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5345607995986938},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.47453033924102783},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.47198110818862915},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41967537999153137},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3654940724372864},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3572963774204254},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1341235339641571},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.09458339214324951}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8278442621231079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778509259223938},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.7158783078193665},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.6444360017776489},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6185650825500488},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5850902795791626},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5675897598266602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5351091027259827},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5345607995986938},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.47453033924102783},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.47198110818862915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41967537999153137},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3654940724372864},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3572963774204254},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1341235339641571},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.09458339214324951},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssrr.2019.8848957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssrr.2019.8848957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1424654272","https://openalex.org/W1522301498","https://openalex.org/W1586173270","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W1931877416","https://openalex.org/W1979266466","https://openalex.org/W1980969546","https://openalex.org/W2024139303","https://openalex.org/W2024908906","https://openalex.org/W2064675550","https://openalex.org/W2104733512","https://openalex.org/W2120353515","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2152671441","https://openalex.org/W2155007355","https://openalex.org/W2155968351","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2296673577","https://openalex.org/W2461937780","https://openalex.org/W2537007072","https://openalex.org/W2567015638","https://openalex.org/W2580175322","https://openalex.org/W2585954273","https://openalex.org/W2593841437","https://openalex.org/W2726187156","https://openalex.org/W2746553466","https://openalex.org/W2950471160","https://openalex.org/W2951799221","https://openalex.org/W2962887844","https://openalex.org/W2962894046","https://openalex.org/W2962957031","https://openalex.org/W2963428623","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W2964043796","https://openalex.org/W2964070888","https://openalex.org/W2964077562","https://openalex.org/W2964121744","https://openalex.org/W2964157221","https://openalex.org/W2964161785","https://openalex.org/W3021208093","https://openalex.org/W3103559770","https://openalex.org/W3124420883","https://openalex.org/W4214717370","https://openalex.org/W4232280717","https://openalex.org/W4297795161","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W6634982934","https://openalex.org/W6638018090","https://openalex.org/W6640174482","https://openalex.org/W6675999342","https://openalex.org/W6682849425","https://openalex.org/W6692405165","https://openalex.org/W6692846177","https://openalex.org/W6696324988","https://openalex.org/W6734582178","https://openalex.org/W6740801417"],"related_works":["https://openalex.org/W2930076404","https://openalex.org/W4253519380","https://openalex.org/W2071957557","https://openalex.org/W2596413128","https://openalex.org/W4391249562","https://openalex.org/W2356867392","https://openalex.org/W2913749762","https://openalex.org/W2321940404","https://openalex.org/W2782776446","https://openalex.org/W3043170174"],"abstract_inverted_index":{"Navigation":[0],"of":[1,83],"mobile":[2],"robots":[3],"in":[4,15,58,93,96,101,122],"unstructured,":[5],"time-varying":[6,30],"environments":[7,128],"is":[8,78,81,91,139],"challenging.":[9],"It":[10],"becomes":[11],"even":[12],"more":[13],"complicated":[14],"disaster":[16],"scenarios":[17,34,95,109],"where":[18],"logistical":[19],"difficulties,":[20],"as":[21,23,27],"well":[22],"technical":[24],"issues":[25],"such":[26],"reactive":[28],"and":[29,98],"obstacles,":[31,112,131],"exist.":[32],"These":[33],"are":[35],"too":[36],"complex":[37,59],"for":[38,56],"classical":[39],"obstacle":[40],"avoidance":[41],"methods":[42],"to":[43,72,117,142],"navigate":[44,118],"through":[45],"successfully.":[46],"This":[47],"paper":[48],"presents":[49],"a":[50,102],"sample":[51],"efficient":[52],"reinforcement":[53],"learning":[54],"algorithm":[55],"navigation":[57],"environments.":[60],"The":[61,89],"approach":[62,77],"augments":[63],"training":[64,85,132],"data":[65,71],"with":[66,86,110,129],"randomly":[67],"generated":[68],"target":[69,121],"location":[70],"accelerate":[73],"learning.":[74],"A":[75],"Q-learning":[76],"implemented,":[79],"which":[80],"capable":[82],"quick":[84],"limited":[87],"episodes.":[88,126],"procedure":[90],"tested":[92],"four":[94],"Gazebo":[97],"one":[99],"scenario":[100],"real-world":[103],"experiment.":[104],"In":[105],"the":[106,113,120,137],"two":[107],"simulation":[108],"no":[111],"method":[114],"can":[115],"learn":[116,143],"towards":[119],"fewer":[123],"than":[124],"200":[125],"For":[127],"moving":[130],"takes":[133],"slightly":[134],"longer,":[135],"but":[136],"process":[138],"still":[140],"able":[141],"an":[144],"effective":[145],"policy":[146],"quickly.":[147]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}