{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T04:17:34Z","timestamp":1783916254806,"version":"3.55.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T00:00:00Z","timestamp":1638662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T00:00:00Z","timestamp":1638662400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T00:00:00Z","timestamp":1638662400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002322","name":"CAPES","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,5]]},"DOI":"10.1109\/ssci50451.2021.9660123","type":"proceedings-article","created":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T21:09:51Z","timestamp":1643058591000},"page":"1-8","source":"Crossref","is-referenced-by-count":19,"title":["Proximal Policy Optimization with Continuous Bounded Action Space via the Beta Distribution"],"prefix":"10.1109","author":[{"given":"Irving G. B.","family":"Petrazzini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric A.","family":"Antonelo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref12","author":"brockman","year":"2016","journal-title":"Onenai gym"},{"key":"ref13","author":"kostrikov","year":"2018","journal-title":"Pytorch implementations of reinforcement learning algorithms"},{"key":"ref14","author":"klimov","year":"0"},{"key":"ref15","author":"klimov","year":"0"},{"key":"ref16","year":"0","journal-title":"OpenAir"},{"key":"ref17","author":"ha","year":"2018","journal-title":"Recurrent world models facilitate policy evolution"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308525"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321817"},{"key":"ref4","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Int Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref6","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Int Conference on Machine Learning"},{"key":"ref5","article-title":"Prox-imal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref8","first-page":"834","article-title":"Improving stochastic policy gradients in continuous control with deep reinforcement learning using the beta distribution","author":"chou","year":"0","journal-title":"Int Conference on Machine Learning"},{"key":"ref7","article-title":"Sample efficient actor-critic with experience replay","author":"wang","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref9","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Weight agnostic neural networks","author":"gaier","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref21","article-title":"Augmenting gail with bc for sample efficient imitation learning","author":"jena","year":"2020","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","location":"Orlando, FL, USA","start":{"date-parts":[[2021,12,5]]},"end":{"date-parts":[[2021,12,7]]}},"container-title":["2021 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9659537\/9659538\/09660123.pdf?arnumber=9660123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:56:28Z","timestamp":1652201788000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9660123\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ssci50451.2021.9660123","relation":{},"subject":[],"published":{"date-parts":[[2021,12,5]]}}}