{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T23:19:06Z","timestamp":1780701546407,"version":"3.54.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF CPS Frontier, Context Aware Learning for Sustainable Cyber-Agricultural Systems","award":["1954556"],"award-info":[{"award-number":["1954556"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tnnls.2025.3641531","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T20:50:44Z","timestamp":1770411044000},"page":"2869-2883","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing PPO With Trajectory-Aware Hybrid Policies"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9553-0789","authenticated-orcid":false,"given":"Qisai","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, Iowa State University, Ames, IA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanhong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Translational AI Center, Iowa State University, Ames, IA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8395-5993","authenticated-orcid":false,"given":"Hsin-Jung","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Iowa State University, Ames, IA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6592-1111","authenticated-orcid":false,"given":"Mahsa","family":"Khosravi","sequence":"additional","affiliation":[{"name":"Department of Industrial and Manufacturing Systems Engineering, Iowa State University, Ames, IA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua R.","family":"Waite","sequence":"additional","affiliation":[{"name":"Translational AI Center, Iowa State University, Ames, IA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6775-9199","authenticated-orcid":false,"given":"Soumik","family":"Sarkar","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Iowa State University, Ames, IA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/614"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117164"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00718"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197132"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2020.3000274"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13898"},{"key":"ref8","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref9","article-title":"Learning to generate better than your LLM","volume-title":"arXiv:2306.11816","author":"Chang","year":"2023"},{"key":"ref10","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. 19th Int. Conf. Mach. Learn.","author":"Kakade"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3026196"},{"key":"ref13","article-title":"Understanding continual learning settings with data distribution drift analysis","author":"Lesort","year":"2021","journal-title":"arXiv:2104.01678"},{"key":"ref14","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3387168.3387199"},{"key":"ref16","article-title":"Variance-reduced off-policy memory-efficient policy search","author":"Lyu","year":"2020","journal-title":"arXiv:2009.06548"},{"key":"ref17","article-title":"Is high variance unavoidable in RL? A case study in continuous control","author":"Bjorck","year":"2021","journal-title":"arXiv:2110.11222"},{"key":"ref18","first-page":"7624","article-title":"An improved analysis of (variance-reduced) policy gradient and natural policy gradient methods","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref19","first-page":"2228","article-title":"On the convergence and sample efficiency of variance-reduced policy gradient method","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref20","first-page":"541","article-title":"An improved convergence analysis of stochastic variance-reduced policy gradient","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Xu"},{"key":"ref21","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Johnson"},{"key":"ref22","article-title":"On stationary point convergence of PPO-clip","volume-title":"Proc. The 12th Int. Conf. Learn. Represent.","author":"Jin"},{"key":"ref23","article-title":"PTR-PPO: Proximal policy optimization with prioritized trajectory replay","author":"Liang","year":"2021","journal-title":"arXiv:2112.03798"},{"key":"ref24","first-page":"11909","article-title":"Generalized proximal policy optimization with sample reuse","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Queeney"},{"key":"ref25","first-page":"1017","article-title":"P3O: Policy-on policy-off policy optimization","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Fakoor"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25864"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26099"},{"key":"ref28","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISIEA58478.2023.10212317"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2024.114065"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2981320"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref33","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref34","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref35","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref36","first-page":"5089","article-title":"Statistically efficient off-policy policy gradients","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kallus"},{"key":"ref37","first-page":"167","article-title":"A nonparametric off-policy policy gradient","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Tosatto"},{"key":"ref38","article-title":"Interpolated policy gradient: Merging on-policy and off-policy gradient estimation for deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Gu"},{"key":"ref39","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8122622"},{"key":"ref41","article-title":"A theoretical analysis of optimistic proximal policy optimization in linear Markov decision processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhong"},{"key":"ref42","first-page":"6726","article-title":"Refined regret for adversarial MDPs with linear function approximation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dai"},{"key":"ref43","first-page":"31117","article-title":"Improved regret for efficient online reinforcement learning with linear function approximation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sherman"},{"key":"ref44","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461918"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1177\/1094428114541701"},{"key":"ref47","first-page":"4473","article-title":"Cautiously optimistic policy optimization and exploration with linear function approximation","volume-title":"Proc. Conf. Learn. Theory","author":"Zanette"},{"key":"ref48","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11549955\/11373061.pdf?arnumber=11373061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:56:43Z","timestamp":1780603003000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11373061\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":48,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3641531","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}