{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T11:11:51Z","timestamp":1730200311241,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"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":[[2020,12,10]]},"DOI":"10.1109\/bigdata50022.2020.9377951","type":"proceedings-article","created":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T17:10:21Z","timestamp":1616173821000},"page":"123-132","source":"Crossref","is-referenced-by-count":0,"title":["State Action Separable Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Ziyao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kin K.","family":"Leung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantinos","family":"Poularakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mudhakar","family":"Srivatsa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Is the policy gradient a gradient?","year":"2020","author":"nota","key":"ref10"},{"key":"ref11","article-title":"Comparing policy-gradient algorithms","author":"sutton","year":"2000","journal-title":"IEEE Transactions on Systems Man and Cybernetics"},{"year":"0","key":"ref12","article-title":"State action separable reinforcement learning appendix"},{"key":"ref13","first-page":"1064","article-title":"The asymptotic convergence-rate of Q-learning","author":"szepesvari","year":"1998","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S1352-2310(97)00447-0"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref16"},{"article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","year":"2018","author":"haarnoja","key":"ref17"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref18"},{"article-title":"Stable baselines","year":"2018","author":"hill","key":"ref19"},{"key":"ref28","first-page":"6118","article-title":"Value prediction network","author":"oh","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref4"},{"article-title":"Learning action-transferable policy with action embedding","year":"2019","author":"chen","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref6","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"},{"article-title":"Reinforcement learning with unsupervised auxiliary tasks","year":"2016","author":"jaderberg","key":"ref29"},{"article-title":"Neural network design","year":"1995","author":"hagan","key":"ref5"},{"article-title":"Off-policy actor-critic","year":"2012","author":"degris","key":"ref8"},{"key":"ref7","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref9","first-page":"1387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0"},{"journal-title":"Introduction to Reinforcement Learning","year":"1998","author":"sutton","key":"ref1"},{"article-title":"How transferable are the representations learned by deep Q agents?","year":"2020","author":"tyo","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013582"},{"article-title":"Estimating q (s, s’) with deep deterministic dynamics gradients","year":"2020","author":"edwards","key":"ref21"},{"article-title":"Decoupling dynamics and reward for transfer learning","year":"2018","author":"zhang","key":"ref24"},{"key":"ref23","article-title":"The bitter lesson","volume":"13","author":"sutton","year":"2019","journal-title":"Incomplete Ideas (blog)"},{"article-title":"Learning action representations for reinforcement learning","year":"2019","author":"chandak","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014384"}],"event":{"name":"2020 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2020,12,10]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2020,12,13]]}},"container-title":["2020 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9377717\/9377728\/09377951.pdf?arnumber=9377951","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T11:51:10Z","timestamp":1656330670000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9377951\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,10]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/bigdata50022.2020.9377951","relation":{},"subject":[],"published":{"date-parts":[[2020,12,10]]}}}