{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T06:37:18Z","timestamp":1729665438719,"version":"3.28.0"},"reference-count":9,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"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":[],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1109\/icip40778.2020.9190994","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T16:45:18Z","timestamp":1601484318000},"page":"3184-3188","source":"Crossref","is-referenced-by-count":4,"title":["Generalized Critic Policy Optimization: A Model For Combining Advantage Estimates In Actor Critic Methods"],"prefix":"10.1109","author":[{"given":"Roumeissa","family":"Kitouni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abderrahim","family":"Kitouni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","first-page":"2016","author":"coumans","year":"0","journal-title":"Pybullet a python module for physics simulation for games robotics and machine learning"},{"journal-title":"OpenAI Gym","year":"2016","author":"brockman","key":"ref3"},{"key":"ref6","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref5","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv preprint arXiv 1506 02349"},{"key":"ref8","article-title":"Reproducibility of benchmarked deep reinforcement learning tasks for continuous control","author":"islam","year":"2017","journal-title":"arXiv preprint arXiv 1708 02562"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2017.09.005"},{"key":"ref2","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"journal-title":"Spinning up in deep reinforcement learning","year":"2018","author":"achiam","key":"ref9"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11694","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"}],"event":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2020,10,25]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2020,10,28]]}},"container-title":["2020 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9184803\/9190635\/09190994.pdf?arnumber=9190994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T06:54:41Z","timestamp":1669013681000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9190994\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":9,"URL":"https:\/\/doi.org\/10.1109\/icip40778.2020.9190994","relation":{},"subject":[],"published":{"date-parts":[[2020,10]]}}}