{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:14:48Z","timestamp":1730254488179,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/icpr.2018.8545231","type":"proceedings-article","created":{"date-parts":[[2018,11,29]],"date-time":"2018-11-29T19:17:38Z","timestamp":1543519058000},"page":"1253-1258","source":"Crossref","is-referenced-by-count":1,"title":["Stabilizing Actor Policies by Approximating Advantage Distributions from K Critics"],"prefix":"10.1109","author":[{"given":"Alfonso B.","family":"Labao","sequence":"first","affiliation":[]},{"given":"Prospero C.","family":"Naval","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Vizdoom Drqn with prioritized experience replay double-q learning & snapshot ensembling","year":"2018","author":"schulze","key":"ref10"},{"key":"ref11","first-page":"2094","article-title":"Deep reinforcement learning with double q-learning.","author":"van hasselt","year":"2016","journal-title":"AAAI"},{"key":"ref12","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref13","article-title":"Interpolated policy gradient: Merging on-policy and off-policy gradient estimation for deep reinforcement learning","volume":"30","author":"gu","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"385","article-title":"Finding structure in reinforcement learning","author":"thrun","year":"1995","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366913"},{"journal-title":"Rainbow Combining Improvements in Deep Reinforcement Learning","year":"2017","author":"hessel","key":"ref16"},{"key":"ref17","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","author":"sutton","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref4","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref3","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref6","first-page":"176","article-title":"Averaged-dqn: Variance reduction and stabilization for deep reinforcement learning","author":"anschel","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref5","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref8","first-page":"5085","article-title":"Arnold: An autonomous agent to play fps games.","author":"chaplot","year":"2017","journal-title":"AAAI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref2","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":"ref1","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080439"}],"event":{"name":"2018 24th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2018,8,20]]},"location":"Beijing","end":{"date-parts":[[2018,8,24]]}},"container-title":["2018 24th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8527858\/8545020\/08545231.pdf?arnumber=8545231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T09:27:00Z","timestamp":1643275620000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8545231\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icpr.2018.8545231","relation":{},"subject":[],"published":{"date-parts":[[2018,8]]}}}