{"id":"https://openalex.org/W7225007722","doi":"https://doi.org/10.5281/zenodo.23808855","title":"Cumulative Stabilization Probabilities During PPO Learning: A Paired Reward Study for Cart-Pendulum Swing-Up","display_name":"Cumulative Stabilization Probabilities During PPO Learning: A Paired Reward Study for Cart-Pendulum Swing-Up","publication_year":2026,"publication_date":"2026-11-01","ids":{"openalex":"https://openalex.org/W7225007722","doi":"https://doi.org/10.5281/zenodo.23808855"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23808855","doi":"https://doi.org/10.5281/zenodo.23808855","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23808855","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23808855","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160261107","display_name":"Shaikhislam Askanbay","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Askanbay, Shaikhislam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5160261107"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":9.999999747378752e-05,"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/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.8399999737739563},{"id":"https://openalex.org/keywords/reward-shaping","display_name":"reward shaping","score":0.6169999837875366},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.4050000011920929}],"concepts":[{"id":"https://openalex.org/C137668524","wikidata":"https://www.wikidata.org/wiki/Q189813","display_name":"Censoring (clinical trials)","level":2,"score":0.5982999801635742},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5532000064849854},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5026999711990356},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.49390000104904175},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4115999937057495},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.288100004196167},{"id":"https://openalex.org/C178518018","wikidata":"https://www.wikidata.org/wiki/Q1024555","display_name":"CUSUM","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C97933134","wikidata":"https://www.wikidata.org/wiki/Q5374249","display_name":"Empirical probability","level":4,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23808855","doi":"https://doi.org/10.5281/zenodo.23808855","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23808855","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.23808856","doi":"https://doi.org/10.5281/zenodo.23808856","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23808856","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23808855","doi":"https://doi.org/10.5281/zenodo.23808855","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23808855","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7220977284","https://openalex.org/W2072492557","https://openalex.org/W4302012246","https://openalex.org/W7223712653","https://openalex.org/W2580769675","https://openalex.org/W4399415955","https://openalex.org/W2165501261","https://openalex.org/W7204794342","https://openalex.org/W6884996802","https://openalex.org/W2944767573"],"abstract_inverted_index":{"This":[0],"simulation":[1],"study":[2],"investigates":[3],"how":[4],"the":[5,28,92],"cumulative":[6],"probability":[7,29],"of":[8,119],"successful":[9],"cart\u2013pendulum":[10],"swing-up":[11],"and":[12,19,63,88,98,158,171],"sustained":[13],"stabilization":[14,38],"changes":[15],"with":[16,114],"training":[17,44,55,130],"progress":[18],"physical":[20],"evaluation":[21],"time.":[22],"The":[23,70,106,144],"target":[24],"quantity,":[25],"H(g,t),":[26],"measures":[27],"that":[30,139],"a":[31,79,115,147],"controller":[32],"has":[33],"completed":[34],"its":[35],"first":[36],"qualifying":[37],"interval":[39,118],"by":[40,103],"time":[41],"t":[42],"at":[43],"generation":[45],"g.":[46],"Two":[47],"reward":[48,141],"formulations":[49],"are":[50,161],"compared":[51],"using":[52,149],"100":[53],"paired":[54,108],"seeds,":[56],"1,000":[57],"PPO":[58],"rollout/update":[59],"generations":[60],"per":[61],"controller,":[62],"full":[64],"20-second":[65],"evaluations":[66],"every":[67],"ten":[68],"generations.":[69],"simulator":[71],"uses":[72],"fully":[73],"nonlinear":[74],"uniform-rod":[75],"dynamics.":[76],"Success":[77],"requires":[78],"simultaneous":[80],"two-second":[81],"hold":[82],"within":[83],"specified":[84],"cart-position,":[85],"cart-velocity,":[86],"upright-angle":[87],"angular-velocity":[89],"tolerances.":[90],"At":[91],"final":[93],"generation,":[94],"68/100":[95],"bounded-reward":[96,153],"controllers":[97,101],"52/100":[99],"quadratic-reward":[100],"succeeded":[102],"20":[104],"seconds.":[105],"observed":[107,152],"difference":[109],"was":[110],"16":[111],"percentage":[112],"points,":[113],"conservative":[116],"95%":[117],"\u22123.461":[120],"to":[121],"+34.184":[122],"points.":[123],"Quadratic":[124],"achieved":[125],"substantial":[126],"success":[127],"earlier":[128],"during":[129],"but":[131],"subsequently":[132],"regressed.":[133],"Final":[134],"completion-time":[135],"curves":[136],"crossed,":[137],"showing":[138],"neither":[140],"uniformly":[142],"dominated.":[143],"comparison":[145],"is":[146],"follow-up":[148],"an":[150],"already":[151],"reference":[154],"arm.":[155],"Failures,":[156],"censoring":[157],"learning":[159],"regressions":[160],"retained.":[162],"Supporting":[163],"material":[164],"provides":[165],"event":[166],"data,":[167],"source":[168],"code,":[169],"configurations":[170],"reproducible":[172],"analysis.":[173]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-11-01T00:00:00"}