{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T05:32:43Z","timestamp":1778823163651,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Plan of China","doi-asserted-by":"publisher","award":["2017YFB1300202"],"award-info":[{"award-number":["2017YFB1300202"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9534005","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Adaptive Advantage Estimation for Actor-Critic Algorithms"],"prefix":"10.1109","author":[{"given":"Yurou","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengyi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref31","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref30","author":"dhariwal","year":"2017","journal-title":"OpenAI Baselines"},{"key":"ref10","first-page":"457","article-title":"Bayesian policy gradient algorithms","author":"ghavamzadeh","year":"0","journal-title":"International Conference on Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374604"},{"key":"ref13","first-page":"1057","article-title":"Policy gradient method for reinforcement learning with function approximation","author":"sutton","year":"0","journal-title":"International Conference on Neural Information Processing Systems"},{"key":"ref14","first-page":"538","author":"weaver","year":"2001","journal-title":"The optimal reward baseline for gradient-based reinforcement learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/GCIS.2009.372"},{"key":"ref16","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"0","journal-title":"International Conference on Neural Information Processing Systems"},{"key":"ref17","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref18","first-page":"64","article-title":"Optimality and approximation with policy gradient methods in markov decision processes","author":"agarwal","year":"0","journal-title":"Conference on Learning Theory"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.05.011"},{"key":"ref28","first-page":"380","article-title":"Value function approximation in reinforcement learning using the fourier basis","author":"konidaris","year":"0","journal-title":"Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref27","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref3","first-page":"2944","article-title":"Learning continuous control policies by stochastic value gradients","author":"heess","year":"0","journal-title":"International Conference on Neural Information Processing Systems"},{"key":"ref6","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3409501.3409517"},{"key":"ref5","article-title":"Global convergence of policy gradient methods for linearized control problems","author":"fazel","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref7","first-page":"3528","article-title":"Gradient estimation using stochastic computation graphs","author":"schulman","year":"0","journal-title":"International Conference on Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.806"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref20","first-page":"1407","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","author":"espeholt","year":"0","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref22","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"80","author":"rashid","year":"0","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102421"},{"key":"ref24","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref23","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"ref26","first-page":"278","article-title":"An analysis of actor\/critic algorithms using eligibility traces: Reinforcement learning with imperfect value function","author":"kimura","year":"0","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref25","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","location":"Shenzhen, China","start":{"date-parts":[[2021,7,18]]},"end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09534005.pdf?arnumber=9534005","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:45:50Z","timestamp":1652197550000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9534005\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9534005","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}