{"id":"https://openalex.org/W2888742002","doi":"https://doi.org/10.48550/arxiv.1808.07982","title":"Proximal Policy Optimization and its Dynamic Version for Sequence Generation","display_name":"Proximal Policy Optimization and its Dynamic Version for Sequence Generation","publication_year":2018,"publication_date":"2018-08-24","ids":{"openalex":"https://openalex.org/W2888742002","doi":"https://doi.org/10.48550/arxiv.1808.07982","mag":"2888742002"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1808.07982","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.07982","pdf_url":"https://arxiv.org/pdf/1808.07982","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W2888742002"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1808.07982","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016343106","display_name":"Yi-Lin Tuan","orcid":"https://orcid.org/0009-0006-0556-515X","observed_orcids":["https://orcid.org/0009-0006-0556-515X"]},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tuan, Yi-Lin","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101427440","display_name":"Jinzhi Zhang","orcid":"https://orcid.org/0000-0001-6430-0502","observed_orcids":["https://orcid.org/0000-0001-6430-0502"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Jinzhi","raw_affiliation_strings":["HuaZhong University of science and technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HuaZhong University of science and technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100680672","display_name":"Yujia Li","orcid":"https://orcid.org/0000-0002-1024-9243","observed_orcids":["https://orcid.org/0000-0002-1024-9243","https://orcid.org/0000-0002-3199-5595"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yujia","raw_affiliation_strings":["HuaZhong University of science and technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HuaZhong University of science and technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747","observed_orcids":["https://orcid.org/0000-0002-9654-5747"]},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lee, Hung-yi","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"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":0.9595000147819519,"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":0.9595000147819519,"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/T10028","display_name":"Topic Modeling","score":0.010099999606609344,"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/T12031","display_name":"Speech and dialogue systems","score":0.009399999864399433,"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":0.9909999966621399},{"id":"https://openalex.org/keywords/sequence-generation","display_name":"sequence generation","score":0.9599999785423279},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.6190000176429749},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.828000009059906},{"id":"https://openalex.org/keywords/chatbots","display_name":"chatbots","score":0.6389999985694885},{"id":"https://openalex.org/keywords/adversarial-machine-learning","display_name":"adversarial learning","score":0.6610000133514404}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6886459589004517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4913250505924225},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32551178336143494},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1609560251235962},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.13331004977226257}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1808.07982","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.07982","pdf_url":"https://arxiv.org/pdf/1808.07982","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1808.07982","doi":"https://doi.org/10.48550/arxiv.1808.07982","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1808.07982","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1808.07982","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.07982","pdf_url":"https://arxiv.org/pdf/1808.07982","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2888742002.pdf","grobid_xml":"https://content.openalex.org/works/W2888742002.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1591706642","https://openalex.org/W2176263492","https://openalex.org/W2487501366","https://openalex.org/W2565378226","https://openalex.org/W2581637843","https://openalex.org/W2593383075","https://openalex.org/W2602963933","https://openalex.org/W2605135824","https://openalex.org/W2610395436","https://openalex.org/W2616969219","https://openalex.org/W2622385665","https://openalex.org/W2736601468","https://openalex.org/W2963559013","https://openalex.org/W2963903950","https://openalex.org/W2964028737"],"related_works":["https://openalex.org/W2964268978","https://openalex.org/W4387058415","https://openalex.org/W7095008446","https://openalex.org/W4415797532","https://openalex.org/W2787188308","https://openalex.org/W3016626426","https://openalex.org/W7213522444","https://openalex.org/W6948157231","https://openalex.org/W2801246332","https://openalex.org/W7126201525"],"abstract_inverted_index":{"In":[0,31],"sequence":[1,70],"generation":[2,71],"task,":[3],"many":[4],"works":[5],"use":[6],"policy":[7,36,40,88],"gradient":[8,37,89],"for":[9,57],"model":[10],"optimization":[11,41],"to":[12],"tackle":[13],"the":[14,20,26,62],"intractable":[15],"backpropagation":[16],"issue":[17],"when":[18],"maximizing":[19],"non-differentiable":[21],"evaluation":[22],"metrics":[23],"or":[24],"fooling":[25],"discriminator":[27],"in":[28],"adversarial":[29],"learning.":[30],"this":[32],"paper,":[33],"we":[34],"replace":[35],"with":[38],"proximal":[39],"(PPO),":[42],"which":[43],"is":[44],"a":[45,54],"proved":[46],"more":[47],"efficient":[48],"reinforcement":[49],"learning":[50],"algorithm,":[51],"and":[52,66,76,84,92],"propose":[53],"dynamic":[55],"approach":[56],"PPO":[58,65,83],"(PPO-dynamic).":[59],"We":[60],"demonstrate":[61],"efficacy":[63],"of":[64],"PPO-dynamic":[67,85],"on":[68],"conditional":[69],"tasks":[72],"including":[73],"synthetic":[74],"experiment":[75],"chit-chat":[77],"chatbot.":[78],"The":[79],"results":[80],"show":[81],"that":[82],"can":[86],"beat":[87],"by":[90],"stability":[91],"performance.":[93]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2018-08-31T00:00:00"}