{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:41Z","timestamp":1737176861450,"version":"3.33.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"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":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10826018","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"1167-1176","source":"Crossref","is-referenced-by-count":0,"title":["A Feedback-based Decision-Making Mechanism for Actor-Critic Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Guang","family":"Yang","sequence":"first","affiliation":[{"name":"Virginia Commonwealth University,Dept. of Computer Science,Richmond,VA,USA"}]},{"given":"Ziye","family":"Geng","sequence":"additional","affiliation":[{"name":"Virginia Commonwealth University,Dept. of Computer Science,Richmond,VA,USA"}]},{"given":"Jiahe","family":"Li","sequence":"additional","affiliation":[{"name":"Virginia Commonwealth University,Dept. of Computer Science,Richmond,VA,USA"}]},{"given":"Yanxiao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Virginia Commonwealth University,Dept. of Electrical and Computer Engineering,Richmond,VA,USA"}]},{"given":"Sherif","family":"Abdelwahed","sequence":"additional","affiliation":[{"name":"Virginia Commonwealth University,Dept. of Electrical and Computer Engineering,Richmond,VA,USA"}]},{"given":"Changqing","family":"Luo","sequence":"additional","affiliation":[{"name":"Virginia Commonwealth University,Dept. of Computer Science,Richmond,VA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"article-title":"A survey of deep reinforcement learning in video games","year":"2019","author":"Shao","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref5","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Proceedings of The 2nd Conference on Robot Learning","volume":"87","author":"Kalashnikov"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-021-00398-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-28865-w"},{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2200\/s00268ed1v01y201005aim009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref12","first-page":"903","article-title":"Practical reinforcement learning in continuous spaces","volume-title":"ICML","author":"Smart"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368199"},{"key":"ref14","article-title":"Continuous control with deep reinforcement learning","volume":"abs\/1509.02971","author":"Lillicrap","year":"2015","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3696-5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/820"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5322-7"},{"article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International Conference on Machine Learning","author":"Fujimoto","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref20","first-page":"2139","article-title":"Data-efficient off-policy policy evaluation for reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Thomas"},{"key":"ref21","article-title":"Safe and efficient off-policy reinforcement learning","volume":"29","author":"Munos","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Mnih"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2107151119"},{"key":"ref24","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Haarnoja"},{"key":"ref25","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Fujimoto"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"International Conference on Learning Representations","author":"Yarats","key":"ref27"},{"article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Yarats","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2020.100022"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"article-title":"Deterministic policy gradient algorithms","volume-title":"International Conference on Machine Learning","author":"Silver","key":"ref32"},{"article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"International Conference on Machine Learning","author":"Duan","key":"ref33"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11694","article-title":"Deep reinforcement learning that matters","volume-title":"AAAI Conference on Artificial Intelligence","author":"Henderson"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20839"},{"article-title":"Fast and accurate deep network learning by exponential linear units (elus)","volume-title":"International Conference on Learning Representations","author":"Clevert","key":"ref36"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","start":{"date-parts":[[2024,12,15]]},"location":"Washington, DC, USA","end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10826018.pdf?arnumber=10826018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:16:24Z","timestamp":1737101784000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10826018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10826018","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}