{"id":"https://openalex.org/W4402351843","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650959","title":"MRHER: Model-based Relay Hindsight Experience Replay for Sequential Object Manipulation Tasks with Sparse Rewards","display_name":"MRHER: Model-based Relay Hindsight Experience Replay for Sequential Object Manipulation Tasks with Sparse Rewards","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351843","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650959"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003223732","display_name":"Yuming Huang","orcid":"https://orcid.org/0009-0005-5383-3780"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Huang","raw_affiliation_strings":["Dongguan University of Technology,School of Computer Science and Technology,Dongguan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dongguan University of Technology,School of Computer Science and Technology,Dongguan,China","institution_ids":["https://openalex.org/I2799850029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039372748","display_name":"Bin Ren","orcid":"https://orcid.org/0000-0001-9563-7175"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Ren","raw_affiliation_strings":["Dongguan University of Technology,International School of Microelectronics,Dongguan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dongguan University of Technology,International School of Microelectronics,Dongguan,China","institution_ids":["https://openalex.org/I2799850029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101504719","display_name":"Ziming Xu","orcid":"https://orcid.org/0000-0003-4763-9357"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziming Xu","raw_affiliation_strings":["Dongguan University of Technology,International School of Microelectronics,Dongguan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dongguan University of Technology,International School of Microelectronics,Dongguan,China","institution_ids":["https://openalex.org/I2799850029"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019820828","display_name":"Lianghong Wu","orcid":"https://orcid.org/0000-0002-9795-0808"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianghong Wu","raw_affiliation_strings":["Dongguan University of Technology,International School of Microelectronics,Dongguan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dongguan University of Technology,International School of Microelectronics,Dongguan,China","institution_ids":["https://openalex.org/I2799850029"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2799850029"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10709","display_name":"Social Robot Interaction and HRI","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.9151479005813599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7881557941436768},{"id":"https://openalex.org/keywords/relay","display_name":"Relay","score":0.7094325423240662},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6079952716827393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46977442502975464},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35028135776519775},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.15227705240249634},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11520132422447205}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.9151479005813599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7881557941436768},{"id":"https://openalex.org/C2778156585","wikidata":"https://www.wikidata.org/wiki/Q174053","display_name":"Relay","level":3,"score":0.7094325423240662},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6079952716827393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46977442502975464},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35028135776519775},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.15227705240249634},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11520132422447205},{"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1980035368","https://openalex.org/W2117629901","https://openalex.org/W2145339207","https://openalex.org/W2810754397","https://openalex.org/W2951001370","https://openalex.org/W2962872206","https://openalex.org/W2970393539","https://openalex.org/W2973229164","https://openalex.org/W3028695364","https://openalex.org/W3094427810","https://openalex.org/W3135286130","https://openalex.org/W3173254652","https://openalex.org/W3190132124","https://openalex.org/W3208335691","https://openalex.org/W4236573885","https://openalex.org/W4285294350","https://openalex.org/W4287167165","https://openalex.org/W4299806248","https://openalex.org/W4300799055","https://openalex.org/W4385462854","https://openalex.org/W4386057729","https://openalex.org/W6616173779","https://openalex.org/W6740801417","https://openalex.org/W6747473740","https://openalex.org/W6767047803","https://openalex.org/W6778594666","https://openalex.org/W6779463497","https://openalex.org/W6780559895","https://openalex.org/W6795637536","https://openalex.org/W6797745118","https://openalex.org/W6802051021"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W3140454661","https://openalex.org/W4245029315","https://openalex.org/W2139970489","https://openalex.org/W1492315459","https://openalex.org/W1512434910","https://openalex.org/W2540910169","https://openalex.org/W3089780453","https://openalex.org/W3148904318","https://openalex.org/W2022803902"],"abstract_inverted_index":{"Sparse":[0],"rewards":[1,25],"pose":[2],"a":[3,50,65,98,123],"significant":[4],"challenge":[5],"to":[6,36,78,143],"achieving":[7],"high":[8],"sample":[9,38,46,145,158],"efficiency":[10,159],"in":[11,17,93,148,160,169],"goal-conditioned":[12],"reinforcement":[13],"learning":[14,81],"(RL).":[15],"Specifically,":[16],"sequential":[18],"manipulation":[19,32],"tasks,":[20,162],"the":[21,30,75,80,83,110,114,119,127,170],"agent":[22],"receives":[23],"failure":[24],"until":[26],"it":[27],"successfully":[28],"completes":[29],"entire":[31],"task,":[33],"which":[34],"leads":[35],"low":[37],"efficiency.":[39],"To":[40],"tackle":[41],"this":[42],"issue":[43],"and":[44,73,117,167,173],"improve":[45],"efficiency,":[47,146],"we":[48,96],"propose":[49],"novel":[51],"model-based":[52,101],"RL":[53],"framework":[54],"called":[55,104],"Model-based":[56],"Relay":[57],"Hindsight":[58,89],"Experience":[59,90],"Replay":[60,91],"(MRHER).":[61],"MRHER":[62,134,155],"breaks":[63],"down":[64],"continuous":[66],"task":[67],"into":[68],"subtasks":[69],"with":[70],"increasing":[71],"complexity":[72],"utilizes":[74],"previous":[76],"subtask":[77],"guide":[79],"of":[82,87,113],"subsequent":[84],"one.":[85],"Instead":[86],"using":[88],"(HER)":[92],"every":[94],"subtask,":[95],"design":[97],"new":[99],"robust":[100],"relabeling":[102,106],"method":[103],"Foresight":[105],"(FR).":[107],"FR":[108],"predicts":[109],"future":[111,129],"trajectory":[112],"hindsight":[115],"state":[116],"relabels":[118],"expected":[120],"goal":[121,124],"as":[122],"achieved":[125],"on":[126],"virtual":[128],"trajectory.":[130],"By":[131],"incorporating":[132],"FR,":[133],"effectively":[135],"captures":[136],"more":[137],"information":[138],"from":[139],"historical":[140],"experiences,":[141],"leading":[142],"improved":[144],"particularly":[147],"object-manipulation":[149],"environments.":[150],"Experimental":[151],"results":[152],"demonstrate":[153],"that":[154],"exhibits":[156],"state-of-the-art":[157],"benchmark":[161],"outperforming":[163],"RHER":[164],"by":[165],"13.79%":[166],"14.29%":[168],"FetchPush-v1":[171],"environment":[172],"FetchPickandPlace-v1":[174],"environment,":[175],"respectively.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}