{"id":"https://openalex.org/W4416234204","doi":"https://doi.org/10.3389/frobt.2025.1567211","title":"Comparative analysis of deep Q-learning algorithms for object throwing using a robot manipulator","display_name":"Comparative analysis of deep Q-learning algorithms for object throwing using a robot manipulator","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416234204","doi":"https://doi.org/10.3389/frobt.2025.1567211","pmid":"https://pubmed.ncbi.nlm.nih.gov/41323501"},"language":"en","primary_location":{"id":"doi:10.3389/frobt.2025.1567211","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frobt.2025.1567211","pdf_url":null,"source":{"id":"https://openalex.org/S2595095599","display_name":"Frontiers in Robotics and AI","issn_l":"2296-9144","issn":["2296-9144"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Robotics and AI","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3389/frobt.2025.1567211","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120353280","display_name":"Mohammad Al Homsi","orcid":null},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Mohammad Al Homsi","raw_affiliation_strings":["Mobile and Intelligent Robots @ Panormus Laboratory (MIRPALab), Department of Engineering, University of Palermo, Palermo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile and Intelligent Robots @ Panormus Laboratory (MIRPALab), Department of Engineering, University of Palermo, Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042907758","display_name":"Maja Trumi\u0107","orcid":"https://orcid.org/0000-0002-2945-8010"},"institutions":[{"id":"https://openalex.org/I4068193","display_name":"University of Belgrade","ror":"https://ror.org/02qsmb048","country_code":"RS","type":"education","lineage":["https://openalex.org/I4068193"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Maja Trumi\u0107","raw_affiliation_strings":["School of Electrical Engineering, University of Belgrade, Belgrade, Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, University of Belgrade, Belgrade, Serbia","institution_ids":["https://openalex.org/I4068193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070192940","display_name":"Adriano Fagiolini","orcid":"https://orcid.org/0000-0001-9943-1975"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Adriano Fagiolini","raw_affiliation_strings":["Mobile and Intelligent Robots @ Panormus Laboratory (MIRPALab), Department of Engineering, University of Palermo, Palermo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile and Intelligent Robots @ Panormus Laboratory (MIRPALab), Department of Engineering, University of Palermo, Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010351972","display_name":"Giansalvo Cirrincione","orcid":"https://orcid.org/0000-0002-2894-4164"},"institutions":[{"id":"https://openalex.org/I4647051","display_name":"Universit\u00e9 de Picardie Jules Verne","ror":"https://ror.org/01gyxrk03","country_code":"FR","type":"education","lineage":["https://openalex.org/I4647051"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Giansalvo Cirrincione","raw_affiliation_strings":["Universit\u00e9 de Picardie Jules Verne, Amiens, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Picardie Jules Verne, Amiens, France","institution_ids":["https://openalex.org/I4647051"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5120353280"],"corresponding_institution_ids":["https://openalex.org/I900890020"],"apc_list":{"value":1900,"currency":"USD","value_usd":2125},"apc_paid":{"value":1900,"currency":"USD","value_usd":2125},"fwci":3.8098,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93762692,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"1567211","last_page":"1567211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4146000146865845,"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":0.4146000146865845,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.251800000667572,"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/T10320","display_name":"Neural Networks and Applications","score":0.041600000113248825,"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/throwing","display_name":"Throwing","score":0.6015999913215637},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5339000225067139},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5246999859809875},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42309999465942383},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.39879998564720154},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.39010000228881836},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.34310001134872437},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3409000039100647},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.3327000141143799}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8300999999046326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6554999947547913},{"id":"https://openalex.org/C207451115","wikidata":"https://www.wikidata.org/wiki/Q12898216","display_name":"Throwing","level":2,"score":0.6015999913215637},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5246999859809875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46630001068115234},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.39879998564720154},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3409000039100647},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.33090001344680786},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30239999294281006},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C2992174615","wikidata":"https://www.wikidata.org/wiki/Q246514","display_name":"Tennis ball","level":3,"score":0.2903999984264374},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C174839445","wikidata":"https://www.wikidata.org/wiki/Q1134386","display_name":"Lock (firearm)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.2590000033378601},{"id":"https://openalex.org/C17511633","wikidata":"https://www.wikidata.org/wiki/Q830694","display_name":"SMT placement equipment","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.25369998812675476}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3389/frobt.2025.1567211","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frobt.2025.1567211","pdf_url":null,"source":{"id":"https://openalex.org/S2595095599","display_name":"Frontiers in Robotics and AI","issn_l":"2296-9144","issn":["2296-9144"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Robotics and AI","raw_type":"journal-article"},{"id":"pmid:41323501","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41323501","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in robotics and AI","raw_type":null},{"id":"pmh:oai:HAL:hal-05398923v1","is_oa":false,"landing_page_url":"https://u-picardie.hal.science/hal-05398923","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Robotics and AI, 2025, 12, &#x27E8;10.3389/frobt.2025.1567211&#x27E9;","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:99c78e5ac1704b60ada7e5d5c0649aed","is_oa":true,"landing_page_url":"https://doaj.org/article/99c78e5ac1704b60ada7e5d5c0649aed","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Robotics and AI, Vol 12 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11466462","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12660075","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:iris.unipa.it:10447/710243","is_oa":true,"landing_page_url":"https://hdl.handle.net/10447/710243","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.3389/frobt.2025.1567211","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frobt.2025.1567211","pdf_url":null,"source":{"id":"https://openalex.org/S2595095599","display_name":"Frontiers in Robotics and AI","issn_l":"2296-9144","issn":["2296-9144"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Robotics and AI","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320329307","display_name":"Science Fund of the Republic of Serbia","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1976935191","https://openalex.org/W2087154810","https://openalex.org/W2116168061","https://openalex.org/W2145339207","https://openalex.org/W2157799919","https://openalex.org/W2195446438","https://openalex.org/W2481219994","https://openalex.org/W2899186968","https://openalex.org/W2912412749","https://openalex.org/W2955161446","https://openalex.org/W2963092423","https://openalex.org/W2997583085","https://openalex.org/W3000691000","https://openalex.org/W3092627351","https://openalex.org/W4225813060","https://openalex.org/W4242867249","https://openalex.org/W4246394278","https://openalex.org/W4285059527","https://openalex.org/W4298857966","https://openalex.org/W4300892457","https://openalex.org/W4362650413","https://openalex.org/W4380992688","https://openalex.org/W4383108277","https://openalex.org/W4385245566","https://openalex.org/W4387197008"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,65,123,140,169],"artificial":[3],"intelligence":[4],"(AI)":[5],"have":[6],"attracted":[7],"significant":[8],"attention":[9,105,226],"due":[10],"to":[11,14,60,130,162,178,218,232,250,272],"AI's":[12],"ability":[13,231],"solve":[15],"complex":[16,183],"problems":[17],"and":[18,25,40,67,80,100,119,167,214,234,275],"the":[19,29,101,145,164,191,199,202,207,210,229,254,265],"rapid":[20],"development":[21],"of":[22,75,116,135,193,206,224,246,261,267],"learning":[23],"algorithms":[24,79,137,249,258],"computational":[26,42],"power.":[27],"Among":[28],"many":[30],"AI":[31],"techniques,":[32],"transformers":[33,48],"stand":[34],"out":[35],"for":[36,216],"their":[37,278],"flexible":[38],"architectures":[39],"high":[41],"capacity.":[43],"Unlike":[44],"traditional":[45],"neural":[46],"networks,":[47],"use":[49,86,223],"mechanisms":[50],"such":[51,126,185],"as":[52,127,186],"self-attention":[53,87,96],"with":[54,97,106,113,236,277],"positional":[55],"encoding,":[56],"which":[57],"enable":[58],"them":[59],"effectively":[61],"capture":[62],"long-range":[63],"dependencies":[64],"sequential":[66],"spatial":[68],"data.":[69],"This":[70,156],"paper":[71,241],"presents":[72],"a":[73,141,149,152,159,187,196,244],"comparison":[74,245],"various":[76],"deep":[77,89,98,107,117],"Q-learning":[78,118],"proposes":[81],"two":[82],"original":[83],"techniques":[84,122],"that":[85],"into":[88],"Q-learning.":[90,108],"The":[91,133,204,222,240],"first":[92],"technique":[93],"is":[94,138],"structured":[95],"Q-learning,":[99],"second":[102],"uses":[103],"multi-head":[104,225],"These":[109,257],"methods":[110],"are":[111,176,259],"compared":[112],"different":[114],"types":[115],"other":[120],"temporal":[121,247],"uncertain":[124],"tasks,":[125],"throwing":[128,148,217],"objects":[129],"unknown":[131,219],"targets.":[132],"performance":[134,180],"these":[136],"evaluated":[139],"simplified":[142],"environment,":[143],"where":[144],"task":[146],"involves":[147],"ball":[150],"using":[151],"robotic":[153],"arm":[154],"manipulator.":[155],"setup":[157],"provides":[158],"controlled":[160],"scenario":[161],"analyze":[163],"algorithms'":[165],"efficiency":[166],"effectiveness":[168],"solving":[170],"dynamic":[171],"control":[172],"problems.":[173],"Additional":[174],"constraints":[175,252],"introduced":[177],"evaluate":[179],"under":[181],"more":[182],"conditions,":[184],"joint":[188,212],"lock":[189],"or":[190,201],"presence":[192],"obstacles":[194],"like":[195],"wall":[197],"near":[198],"robot":[200],"target.":[203],"output":[205],"algorithm":[208],"includes":[209,243],"correct":[211],"configurations":[213],"trajectories":[215],"target":[220],"positions.":[221],"has":[227],"enhanced":[228],"robot's":[230,255],"prioritize":[233],"interact":[235,273],"critical":[237],"environmental":[238],"features.":[239],"also":[242],"difference":[248],"address":[251],"on":[253],"joints.":[256],"capable":[260],"finding":[262],"solutions":[263],"within":[264],"limitations":[266],"existing":[268],"hardware,":[269],"enabling":[270],"robots":[271],"intelligently":[274],"autonomously":[276],"environment.":[279]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-11-14T00:00:00"}
