{"id":"https://openalex.org/W4404222686","doi":"https://doi.org/10.54254/2755-2721/101/20240943","title":"Enhancing stability and explainability in reinforcement learning with machine learning","display_name":"Enhancing stability and explainability in reinforcement learning with machine learning","publication_year":2024,"publication_date":"2024-11-08","ids":{"openalex":"https://openalex.org/W4404222686","doi":"https://doi.org/10.54254/2755-2721/101/20240943"},"language":"en","primary_location":{"id":"doi:10.54254/2755-2721/101/20240943","doi":"https://doi.org/10.54254/2755-2721/101/20240943","is_oa":true,"landing_page_url":"http://dx.doi.org/10.54254/2755-2721/101/20240943","pdf_url":"https://ace.ewapub.com/article/view/16587.pdf","source":{"id":"https://openalex.org/S4387281889","display_name":"Applied and Computational Engineering","issn_l":"2755-2721","issn":["2755-2721","2755-273X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied and Computational Engineering","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ace.ewapub.com/article/view/16587.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025239419","display_name":"Yinhe Chen","orcid":"https://orcid.org/0009-0003-5368-918X","observed_orcids":["https://orcid.org/0009-0003-5368-918X"]},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yinhe Chen","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5025239419"],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14129254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"101","issue":"1","first_page":"25","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T11574","display_name":"Artificial Intelligence in Games","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"}},{"id":"https://openalex.org/T13904","display_name":"Artificial Intelligence Applications","score":0.0,"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/reinforcement-learning","display_name":"reinforcement learning","score":0.7839999794960022},{"id":"https://openalex.org/keywords/training-stability","display_name":"training stability","score":0.9350000023841858},{"id":"https://openalex.org/keywords/interpretable-models","display_name":"interpretable models","score":0.7450000047683716},{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.9350000023841858},{"id":"https://openalex.org/keywords/gradient-boosted-decision-trees","display_name":"gradient boosting decision tree","score":0.9179999828338623},{"id":"https://openalex.org/keywords/breakout","display_name":"breakout","score":0.6919999718666077},{"id":"https://openalex.org/keywords/atari-games","display_name":"Atari games","score":0.8220000267028809}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6021248698234558},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5747371912002563},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5656766891479492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3808889389038086},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3594963550567627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33257728815078735},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2625090181827545},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10714364051818848}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.54254/2755-2721/101/20240943","doi":"https://doi.org/10.54254/2755-2721/101/20240943","is_oa":true,"landing_page_url":"http://dx.doi.org/10.54254/2755-2721/101/20240943","pdf_url":"https://ace.ewapub.com/article/view/16587.pdf","source":{"id":"https://openalex.org/S4387281889","display_name":"Applied and Computational Engineering","issn_l":"2755-2721","issn":["2755-2721","2755-273X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied and Computational Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.54254/2755-2721/101/20240943","doi":"https://doi.org/10.54254/2755-2721/101/20240943","is_oa":true,"landing_page_url":"http://dx.doi.org/10.54254/2755-2721/101/20240943","pdf_url":"https://ace.ewapub.com/article/view/16587.pdf","source":{"id":"https://openalex.org/S4387281889","display_name":"Applied and Computational Engineering","issn_l":"2755-2721","issn":["2755-2721","2755-273X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied and Computational Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404222686.pdf","grobid_xml":"https://content.openalex.org/works/W4404222686.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"In":[0],"the":[1,46,79,84,87,92,143,167,173,177,189],"field":[2],"of":[3,48,148,176,192],"reinforcement":[4,26,53,75,123,193],"learning,":[5,54],"training":[6,32,95,149],"agents":[7,77,125],"using":[8],"machine":[9],"learning":[10,27,76,124,194],"algorithms":[11,60,134],"to":[12,72,111],"learn":[13],"and":[14,34,50,67,97,104,107,138,151,159,198],"perform":[15],"tasks":[16],"in":[17,41,52,78,128,195],"complex":[18,129,205],"environments":[19],"has":[20,119,145,169],"become":[21],"a":[22],"prevalent":[23],"approach.":[24],"However,":[25],"faces":[28],"challenges":[29],"such":[30],"as":[31,91],"instability":[33],"decision":[35,160,181],"opacity,":[36],"which":[37],"limit":[38],"its":[39],"feasibility":[40],"real-world":[42,196],"applications.":[43],"To":[44],"solve":[45],"problems":[47],"stability":[49],"transparency":[51],"this":[55],"project":[56],"will":[57],"use":[58],"advanced":[59,133],"like":[61,135],"Proximal":[62],"Policy":[63],"Optimization":[64],"(PPO),":[65],"Q-DAGGER,":[66,137],"Gradient":[68,139],"Boosting":[69,140],"Decision":[70,141],"Trees":[71],"set":[73],"up":[74],"OpenAI":[80],"Gymnasium":[81],"environment.":[82],"Specifically,":[83],"study":[85,118,144,168],"selected":[86],"Atari":[88],"game":[89,98,153],"Breakout":[90],"testbed,":[93],"enhancing":[94,180],"efficiency":[96],"performance":[99,154],"by":[100,163],"refining":[101],"reward":[102,157],"structures":[103,158],"decision-making":[105],"processes,":[106],"integrating":[108,164],"interpretable":[109,165],"models":[110],"provide":[112,185],"explanations":[113],"for":[114,188,202],"agent":[115],"decisions.":[116],"This":[117],"successfully":[120],"developed":[121],"robust":[122],"that":[126],"excel":[127],"environments.":[130],"By":[131],"employing":[132],"PPO,":[136],"Trees,":[142],"addressed":[146],"issues":[147],"instability,":[150],"improved":[152],"through":[155],"optimized":[156],"processes.":[161],"Additionally,":[162],"models,":[166],"provided":[170],"insights":[171,201],"into":[172],"learned":[174],"strategies":[175],"agents,":[178],"thereby":[179],"transparency.":[182],"These":[183],"findings":[184],"crucial":[186],"support":[187],"broader":[190],"application":[191],"scenarios":[197],"offer":[199],"valuable":[200],"tackling":[203],"other":[204],"tasks.":[206]},"counts_by_year":[],"updated_date":"2026-09-21T07:43:02.447757","created_date":"2025-10-10T00:00:00"}