{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:06:18Z","timestamp":1767182778556,"version":"3.44.0"},"reference-count":13,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007270","name":"University of Michigan","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007270","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,8]]},"DOI":"10.23919\/acc63710.2025.11107721","type":"proceedings-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:17:51Z","timestamp":1755800271000},"page":"3073-3078","source":"Crossref","is-referenced-by-count":3,"title":["Generalized Advantage Estimation for Distributional Policy Gradients"],"prefix":"10.23919","author":[{"given":"Shahil","family":"Shaik","sequence":"first","affiliation":[{"name":"Clemson University,Mechanical Engineering Department"}]},{"given":"Jonathon M.","family":"Smereka","sequence":"additional","affiliation":[{"name":"Ground Vehicle Systems Center U.S. Army CCDC"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Clemson University,Mechanical Engineering Department"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"article-title":"Trust Region Policy Optimization","year":"2015","author":"Schulman","key":"ref2"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"Schulman","key":"ref3"},{"key":"ref4","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"issue":"2","key":"ref5","first-page":"229","article-title":"Reinforcement learning: An introduction","volume":"17","author":"Sutton","year":"1999","journal-title":"Robotica"},{"article-title":"Asynchronous Methods for Deep Reinforcement Learning","year":"2016","author":"Mnih","key":"ref6"},{"key":"ref7","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"International conference on machine learning","author":"Bellemare"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-20828-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref11","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"International conference on machine learning","author":"Arjovsky"},{"article-title":"Soft actor-critic algorithms and applications","year":"2018","author":"Haarnoja","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"}],"event":{"name":"2025 American Control Conference (ACC)","start":{"date-parts":[[2025,7,8]]},"location":"Denver, CO, USA","end":{"date-parts":[[2025,7,10]]}},"container-title":["2025 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11107441\/11107442\/11107721.pdf?arnumber=11107721","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:34:51Z","timestamp":1755840891000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11107721\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,8]]},"references-count":13,"URL":"https:\/\/doi.org\/10.23919\/acc63710.2025.11107721","relation":{},"subject":[],"published":{"date-parts":[[2025,7,8]]}}}