{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T03:55:15Z","timestamp":1777089315153,"version":"3.51.4"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tg.2024.3408298","type":"journal-article","created":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T17:48:41Z","timestamp":1717436921000},"page":"158-166","source":"Crossref","is-referenced-by-count":5,"title":["Partial Advantage Estimator for Proximal Policy Optimization"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8923-2562","authenticated-orcid":false,"given":"Yizhao","family":"Jin","sequence":"first","affiliation":[{"name":"Game AI group, Queen Mary University of London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6792-5788","authenticated-orcid":false,"given":"Xiulei","family":"Song","sequence":"additional","affiliation":[{"name":"AI Research Group, JumpW, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4060-5226","authenticated-orcid":false,"given":"Gregory","family":"Slabaugh","sequence":"additional","affiliation":[{"name":"Electrical Engineering and Computer Science, Queen Mary University of London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3180-7451","authenticated-orcid":false,"given":"Simon","family":"Lucas","sequence":"additional","affiliation":[{"name":"Game AI group, Queen Mary University of London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2","article-title":"An analysis of actor\/critic algorithms using eligibility traces: Reinforcement learning with imperfect value function","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kimura","year":"1998"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref3","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref6","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"issue":"1","key":"ref7","first-page":"6859","article-title":"Truncated emphatic temporal difference methods for prediction and control","volume":"23","author":"Zhang","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50021-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12202"},{"key":"ref11","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Int. Conf Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref12","first-page":"1","article-title":"A natural policy gradient","volume":"14","author":"Kakade","year":"2001","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref13","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver","year":"2014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref15","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","year":"2018"},{"key":"ref16","article-title":"Maximum a posteriori policy optimisation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Abdolmaleki","year":"2018"},{"key":"ref17","first-page":"5015","article-title":"The mirage of action-dependent baselines in reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Tucker","year":"2018"},{"key":"ref18","first-page":"1407","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Espeholt","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref20","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Peng","year":"2019"},{"key":"ref21","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref22","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare","year":"2017"},{"key":"ref23","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dabney","year":"2018"},{"key":"ref24","article-title":"Gym-mujoco"},{"key":"ref25","article-title":"Microrts","author":"Villar","year":"2017"},{"key":"ref26","first-page":"3","article-title":"Implementation matters in deep policy gradients: A case study on PPO and TRPO","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Engstrom","year":"2020"},{"issue":"32","key":"ref27","first-page":"15849","article-title":"Reconciling modern machine-learning practice and the classical biasvariance trade-off","volume-title":"Proc. Nat. Acad. Sci.","volume":"116","author":"Belkin","year":"2019"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782673\/10931171\/10546313.pdf?arnumber=10546313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T04:57:53Z","timestamp":1742360273000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10546313\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":27,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tg.2024.3408298","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}