{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T13:02:31Z","timestamp":1771074151808,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,19]]},"DOI":"10.1145\/3788731.3788745","type":"proceedings-article","created":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T11:49:28Z","timestamp":1771069768000},"page":"86-90","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TA-PPO: A Proximal Policy Optimization Method Integrating Temporal Sequence States"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7323-898X","authenticated-orcid":false,"given":"Weijun","family":"Wang","sequence":"first","affiliation":[{"name":"College of Navigation, Jimei University, Xiamen, Fujian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2126-9343","authenticated-orcid":false,"given":"Mingjie","family":"Li","sequence":"additional","affiliation":[{"name":"College of Navigation, Jimei University, Xiamen, Fujian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2269-6576","authenticated-orcid":false,"given":"Bushuo","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Navigation, Jimei University, Xiamen, Fujian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9007-7812","authenticated-orcid":false,"given":"Kuoyuan","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Navigation, Jimei University, Xiamen, Fujian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,2,14]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016. OpenAI Gym. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1606.01540 (2016)."},{"key":"e_1_3_3_1_3_2","unstructured":"H. Huang R. Zhang and M. Li. 2023. Lightweight Temporal Fusion for Reinforcement Learning in Partially Observable Environments. IEEE Robotics and Automation Letters 8 5 (2023) 2451\u20132458."},{"key":"e_1_3_3_1_4_2","unstructured":"T. Huang X. Li and J. Wang. 2024. Recent Advances in Deep Reinforcement Learning: A Comprehensive Survey. Artificial Intelligence Review 58 3 (2024) 1841\u20131882."},{"key":"e_1_3_3_1_5_2","unstructured":"Leslie\u00a0P. Kaelbling Michael\u00a0L. Littman and Andrew\u00a0W. Moore. 2023. Reinforcement Learning: A Survey (Revisited Edition). Foundations and Trends in Machine Learning 16 2 (2023) 95\u2013210."},{"key":"e_1_3_3_1_6_2","first-page":"8121","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Kim J.","year":"2024","unstructured":"J. Kim, D. Park, and S. Oh. 2024. Temporal-Aware Reinforcement Learning via History Compression. In Proceedings of the AAAI Conference on Artificial Intelligence , Vol.\u00a038. 8121\u20138129."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"B.\u00a0R. Kiran I. Sobh V. Talpaert P. Mannion A.\u00a0A.\u00a0Al Sallab S. Yogamani and P. P\u00e9rez. 2022. Deep Reinforcement Learning for Autonomous Driving: A Survey. IEEE Transactions on Intelligent Transportation Systems 23 8 (2022) 14212\u201314238.","DOI":"10.1109\/TITS.2021.3054625"},{"key":"e_1_3_3_1_8_2","unstructured":"R. Luo J. Zhu Z. Huang et\u00a0al. 2024. Efficient Policy Optimization with Time-Series Embedding Networks. IEEE Access 12 (2024) 48891\u201348904."},{"key":"e_1_3_3_1_9_2","unstructured":"A.\u00a0S. Polydoros and L. Nalpantidis. 2023. Survey of Model-Based Reinforcement Learning in Robotics. Robotics and Autonomous Systems 159 (2023) 104324."},{"key":"e_1_3_3_1_10_2","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1707.06347 (2017)."},{"key":"e_1_3_3_1_11_2","unstructured":"X. Wang C. Li and D. Zhang. 2024. Adaptive Proximal Policy Optimization with Dynamic Clipping for Stable Reinforcement Learning. Neurocomputing 568 (2024) 126915."},{"key":"e_1_3_3_1_12_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Xu T.","year":"2023","unstructured":"T. Xu, H. Liu, W. Zhao, and K. Li. 2023. PPO-TD: Proximal Policy Optimization with Temporal Difference Regularization. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_1_13_2","unstructured":"T. Zhang H. Wang and Y. Liu. 2024. A Survey on Recent Advances in Proximal Policy Optimization and Its Variants. Artificial Intelligence Review 58 4 (2024) 2121\u20132156."}],"event":{"name":"EILM 2025: 2025 International Conference on Embodied Intelligence and Large Models","location":"Chengdu China","acronym":"EILM 2025"},"container-title":["Proceedings of the 2025 International Conference on Embodied Intelligence and Large Models"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3788731.3788745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T12:09:20Z","timestamp":1771070960000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788731.3788745"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,19]]},"references-count":12,"alternative-id":["10.1145\/3788731.3788745","10.1145\/3788731"],"URL":"https:\/\/doi.org\/10.1145\/3788731.3788745","relation":{},"subject":[],"published":{"date-parts":[[2025,12,19]]},"assertion":[{"value":"2026-02-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}