{"id":"https://openalex.org/W4408353634","doi":"https://doi.org/10.1109/icassp49660.2025.10889202","title":"Integrating Failures in Robot Skill Acquisition with Offline Action-Sequence Diffusion RL","display_name":"Integrating Failures in Robot Skill Acquisition with Offline Action-Sequence Diffusion RL","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353634","doi":"https://doi.org/10.1109/icassp49660.2025.10889202"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5091130042","display_name":"Hecheng Wang","orcid":"https://orcid.org/0000-0001-9873-1626"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hecheng Wang","raw_affiliation_strings":["Fudan University,Academy for Engineering & Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering & Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009450745","display_name":"Lizhe Qi","orcid":"https://orcid.org/0000-0002-4348-1559"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhe Qi","raw_affiliation_strings":["Fudan University,Academy for Engineering & Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering & Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005919686","display_name":"Yunquan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunquan Sun","raw_affiliation_strings":["Fudan University,Academy for Engineering & Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering & Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091130042"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.1038,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74533038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9952999949455261,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9952999949455261,"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/T10571","display_name":"Robotic Mechanisms and Dynamics","score":0.9818000197410583,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9642999768257141,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7002532482147217},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6791034936904907},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6173211336135864},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5771225690841675},{"id":"https://openalex.org/keywords/dreyfus-model-of-skill-acquisition","display_name":"Dreyfus model of skill acquisition","score":0.4624936878681183},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.46141916513442993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4077773690223694},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3544701933860779},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3383411765098572}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7002532482147217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6791034936904907},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6173211336135864},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5771225690841675},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.4624936878681183},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.46141916513442993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4077773690223694},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3544701933860779},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3383411765098572},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W3016361525","https://openalex.org/W3094558535","https://openalex.org/W3174849255","https://openalex.org/W4200072825","https://openalex.org/W4385403811","https://openalex.org/W4385430674","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6783713337","https://openalex.org/W6796589144","https://openalex.org/W6799150178","https://openalex.org/W6800425027","https://openalex.org/W6800774826","https://openalex.org/W6802366246","https://openalex.org/W6802659552","https://openalex.org/W6838833932","https://openalex.org/W6841549819","https://openalex.org/W6855028510","https://openalex.org/W6857454988","https://openalex.org/W6857937820","https://openalex.org/W6858636673"],"related_works":["https://openalex.org/W8302103","https://openalex.org/W3171631314","https://openalex.org/W2674584172","https://openalex.org/W2967743314","https://openalex.org/W2606825221","https://openalex.org/W2184085865","https://openalex.org/W2064245428","https://openalex.org/W2170721890","https://openalex.org/W2122871747","https://openalex.org/W1990892711"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,65,172],"robot":[3,22],"learning":[4,90],"leverage":[5],"large":[6,33],"language":[7,118],"models":[8],"(LLMs)":[9],"and":[10,13,20,31,45,63,85,117,177],"sampling-based":[11],"task":[12],"motion":[14],"planning":[15],"(TAMP)":[16],"modules":[17],"for":[18,94],"automatic":[19],"scalable":[21],"data":[23,44,71,184],"generation.":[24],"This":[25],"method":[26,62,167,190],"yields":[27],"both":[28],"success":[29,130,175,201,207],"trajectories":[30],"a":[32,66,80],"number":[34],"of":[35,60,103,110,161,174],"failure":[36,43,183],"trajectories.":[37],"Prior":[38],"works":[39],"typically":[40],"filter":[41],"out":[42],"adopt":[46],"behavior":[47,73],"cloning":[48],"(BC)":[49],"to":[50,124,185,195],"train":[51],"policy.":[52,74],"However,":[53],"this":[54,76],"significantly":[55,168],"reduces":[56],"the":[57,61,70,100,104,108,126,129,135,141,146,154,158,162,187,199],"sample":[58,178],"efficiency":[59],"results":[64,193],"policy":[67,84,89,127],"limited":[68],"by":[69,139],"collection":[72],"In":[75],"paper,":[77],"we":[78,133,150],"introduce":[79],"vision-language-conditioned":[81],"action-sequence":[82,87,136],"diffusion":[83,88,105,164],"an":[86],"with":[91,198],"Q-guided":[92],"refinement":[93],"its":[95],"training.":[96],"We":[97,120],"first":[98],"redefine":[99],"reverse":[101,163],"process":[102],"model":[106],"as":[107],"distribution":[109],"action":[111],"sequences":[112],"conditioned":[113],"on":[114,128],"visual":[115],"observations":[116],"instructions.":[119],"then":[121],"employ":[122],"BC":[123,159],"pretrain":[125],"sub-dataset.":[131],"Next,":[132],"optimize":[134,186],"Q-value":[137,155],"function":[138,156],"minimizing":[140],"temporal":[142],"difference":[143],"error":[144],"across":[145],"complete":[147,200],"dataset.":[148],"Finally,":[149],"integrate":[151],"guidance":[152],"from":[153],"into":[157],"loss":[160],"chain.":[165],"Our":[166],"outperforms":[169],"baseline":[170],"methods":[171],"terms":[173],"rate":[176],"efficiency.":[179],"By":[180],"effectively":[181],"leveraging":[182],"policy,":[188],"our":[189],"can":[191],"achieve":[192],"comparable":[194],"those":[196],"trained":[197],"sub-dataset":[202],"while":[203],"requiring":[204],"20%-30%":[205],"less":[206],"data.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}