{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:52:22Z","timestamp":1740102742933,"version":"3.37.3"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446437","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced Deep Reinforcement Learning for Parcel Singulation in Non-Stationary Environments"],"prefix":"10.1109","author":[{"given":"Jiwei","family":"Shen","sequence":"first","affiliation":[{"name":"East China Normal University,School of Communications and Electronic Engineering,Shanghai,China"}]},{"given":"Hu","family":"Lu","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Communications and Electronic Engineering,Shanghai,China"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Communications and Electronic Engineering,Shanghai,China"}]},{"given":"Shujing","family":"Lyu","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Communications and Electronic Engineering,Shanghai,China"}]},{"given":"Yue","family":"Lu","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Communications and Electronic Engineering,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.15.2314.0081"},{"key":"ref2","first-page":"11784","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Kumar","year":"2019"},{"key":"ref3","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Agarwal"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC.2016.7763454"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460756"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3335416"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403315"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968560"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IECON43393.2020.9255016"},{"key":"ref15","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"International conference on machine learning","author":"Duan"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref17","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3333238"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446437.pdf?arnumber=10446437","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:16:36Z","timestamp":1722575796000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446437\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446437","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}