{"id":"https://openalex.org/W4386323795","doi":"https://doi.org/10.1109/isie51358.2023.10228056","title":"Deep Q-Learning versus Proximal Policy Optimization: Performance Comparison in a Material Sorting Task","display_name":"Deep Q-Learning versus Proximal Policy Optimization: Performance Comparison in a Material Sorting Task","publication_year":2023,"publication_date":"2023-06-19","ids":{"openalex":"https://openalex.org/W4386323795","doi":"https://doi.org/10.1109/isie51358.2023.10228056"},"language":"en","primary_location":{"id":"doi:10.1109/isie51358.2023.10228056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isie51358.2023.10228056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 32nd International Symposium on Industrial Electronics (ISIE)","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/A5056310373","display_name":"Reuf Kozlica","orcid":"https://orcid.org/0000-0003-1872-1685"},"institutions":[{"id":"https://openalex.org/I4210159430","display_name":"P\u00e4dagogische Hochschule Salzburg","ror":"https://ror.org/05q3g7p38","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210159430"]},{"id":"https://openalex.org/I4210087982","display_name":"Salzburg University of Applied Sciences","ror":"https://ror.org/0072dxg89","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210087982"]},{"id":"https://openalex.org/I182212641","display_name":"University of Salzburg","ror":"https://ror.org/05gs8cd61","country_code":"AT","type":"education","lineage":["https://openalex.org/I182212641"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Reuf Kozlica","raw_affiliation_strings":["Salzburg University of Applied Sciences,Information Technologies and Digitalisation,Salzburg,Austria","Information Technologies and Digitalisation, Salzburg University of Applied Sciences, Salzburg, Austria"],"affiliations":[{"raw_affiliation_string":"Salzburg University of Applied Sciences,Information Technologies and Digitalisation,Salzburg,Austria","institution_ids":["https://openalex.org/I4210087982","https://openalex.org/I182212641","https://openalex.org/I4210159430"]},{"raw_affiliation_string":"Information Technologies and Digitalisation, Salzburg University of Applied Sciences, Salzburg, Austria","institution_ids":["https://openalex.org/I4210087982"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026447617","display_name":"Stefan Wegenkittl","orcid":"https://orcid.org/0000-0002-3297-7997"},"institutions":[{"id":"https://openalex.org/I4210087982","display_name":"Salzburg University of Applied Sciences","ror":"https://ror.org/0072dxg89","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210087982"]},{"id":"https://openalex.org/I182212641","display_name":"University of Salzburg","ror":"https://ror.org/05gs8cd61","country_code":"AT","type":"education","lineage":["https://openalex.org/I182212641"]},{"id":"https://openalex.org/I4210159430","display_name":"P\u00e4dagogische Hochschule Salzburg","ror":"https://ror.org/05q3g7p38","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210159430"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Stefan Wegenkittl","raw_affiliation_strings":["Salzburg University of Applied Sciences,Information Technologies and Digitalisation,Salzburg,Austria","Information Technologies and Digitalisation, Salzburg University of Applied Sciences, Salzburg, Austria"],"affiliations":[{"raw_affiliation_string":"Salzburg University of Applied Sciences,Information Technologies and Digitalisation,Salzburg,Austria","institution_ids":["https://openalex.org/I4210087982","https://openalex.org/I182212641","https://openalex.org/I4210159430"]},{"raw_affiliation_string":"Information Technologies and Digitalisation, Salzburg University of Applied Sciences, Salzburg, Austria","institution_ids":["https://openalex.org/I4210087982"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114078773","display_name":"Simon Hir\u00e4nder","orcid":null},"institutions":[{"id":"https://openalex.org/I182212641","display_name":"University of Salzburg","ror":"https://ror.org/05gs8cd61","country_code":"AT","type":"education","lineage":["https://openalex.org/I182212641"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Simon Hir\u00e4nder","raw_affiliation_strings":["Paris Lodron University Salzburg,Artificial Intelligence and Human Interfaces,Salzburg,Austria","Artificial Intelligence and Human Interfaces, Paris Lodron University Salzburg, Salzburg, Austria"],"affiliations":[{"raw_affiliation_string":"Paris Lodron University Salzburg,Artificial Intelligence and Human Interfaces,Salzburg,Austria","institution_ids":["https://openalex.org/I182212641"]},{"raw_affiliation_string":"Artificial Intelligence and Human Interfaces, Paris Lodron University Salzburg, Salzburg, Austria","institution_ids":["https://openalex.org/I182212641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056310373"],"corresponding_institution_ids":["https://openalex.org/I182212641","https://openalex.org/I4210087982","https://openalex.org/I4210159430"],"apc_list":null,"apc_paid":null,"fwci":3.4686,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.92625857,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T11741","display_name":"Flexible and Reconfigurable Manufacturing Systems","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T11195","display_name":"Simulation Techniques and Applications","score":0.9908999800682068,"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":0.8890615701675415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7971140146255493},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.6773737668991089},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6316701769828796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6210443377494812},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5989056825637817},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5111752152442932},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4970116913318634},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4412339925765991},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.4332989454269409},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.42263075709342957},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27668651938438416},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10578170418739319}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8890615701675415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971140146255493},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.6773737668991089},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6316701769828796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6210443377494812},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5989056825637817},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5111752152442932},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4970116913318634},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4412339925765991},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.4332989454269409},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.42263075709342957},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27668651938438416},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10578170418739319},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isie51358.2023.10228056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isie51358.2023.10228056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 32nd International Symposium on Industrial Electronics (ISIE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1124044266","https://openalex.org/W1771410628","https://openalex.org/W1977655452","https://openalex.org/W2107726111","https://openalex.org/W2139418546","https://openalex.org/W2145339207","https://openalex.org/W2736601468","https://openalex.org/W2980724475","https://openalex.org/W3008389987","https://openalex.org/W3136347463","https://openalex.org/W3200738313","https://openalex.org/W3204939383","https://openalex.org/W3205041129","https://openalex.org/W4298857966","https://openalex.org/W4312976730","https://openalex.org/W4319717576"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2937181779"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,22,28],"comparison":[4],"between":[5],"two":[6,45],"well-known":[7],"deep":[8,107],"Reinforcement":[9],"Learning":[10],"(RL)":[11],"algorithms:":[12],"Deep":[13],"Q-Learning":[14],"(DQN)":[15],"and":[16,60,66,97,123],"Proximal":[17],"Policy":[18],"optimization":[19],"(PPO)":[20],"in":[21,38,78,92,109],"simulated":[23],"production":[24,112],"system.":[25],"We":[26],"utilize":[27],"Petri":[29],"Net":[30],"(PN)-based":[31],"simulation":[32],"environment,":[33],"which":[34],"was":[35],"previously":[36],"proposed":[37],"related":[39],"work.":[40],"The":[41,71,84,100],"performance":[42],"of":[43,57,68,80,89,106,111,120],"the":[44,87,104,118],"algorithms":[46,91,122],"is":[47],"compared":[48],"based":[49],"on":[50],"several":[51],"evaluation":[52,82],"metrics,":[53],"including":[54],"average":[55,63],"percentage":[56,67],"correctly":[58],"assembled":[59],"sorted":[61],"products,":[62],"episode":[64],"length,":[65],"successful":[69],"episodes.":[70],"results":[72],"show":[73],"that":[74],"PPO":[75],"outperforms":[76],"DQN":[77],"terms":[79],"all":[81],"metrics.":[83],"study":[85,101],"highlights":[86],"advantages":[88],"policy-based":[90],"problems":[93],"with":[94],"high-dimensional":[95],"state":[96],"action":[98],"spaces.":[99],"contributes":[102],"to":[103],"field":[105],"RL":[108],"context":[110],"systems":[113],"by":[114],"providing":[115],"insights":[116],"into":[117],"effectiveness":[119],"different":[121,127],"their":[124],"suitability":[125],"for":[126],"tasks.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}