{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:43:22Z","timestamp":1772905402130,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650965","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Adaptive Spiking TD3+BC for Offline-to-Online Spiking Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xiangfei","family":"Yang","sequence":"first","affiliation":[{"name":"Westlake University,School of Engineering,Hangzhou,China,310024"}]},{"given":"Jian","family":"Song","sequence":"additional","affiliation":[{"name":"Westlake University,School of Engineering,Hangzhou,China,310024"}]},{"given":"Xuetao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications,Xi’an,China,710049"}]},{"given":"Donglin","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University,School of Engineering,Hangzhou,China,310024"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107447615"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(97)00011-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3059172"},{"key":"ref4","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref5","volume-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3128379"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2019.00883"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01238"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340948"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17180"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.08.009"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3198259"},{"key":"ref13","first-page":"2016","article-title":"Deep reinforcement learning with population-coded spiking neural network for continuous control","volume-title":"proceedings of Conference on Robot Learning","author":"Tang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19879"},{"key":"ref15","article-title":"Distilling neuron spike with high temperature in reinforcement learning agents","author":"Zhang","year":"2021"},{"key":"ref16","article-title":"Offline reinforcement learning: tutorial, review, and perspectives on open problems","author":"Sergey","year":"2020"},{"key":"ref17","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"the proceedings of Thirty-Fifth Conference on Neural Information Processing Systems","volume":"34","author":"Fujimoto"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.14428\/esann\/2022.ES2022-110"},{"key":"ref19","first-page":"1702","article-title":"Offline-to-online reinforcement learning via balanced replay and pessimistic q-ensemble","volume-title":"proceedings of Conference on Robot Learning","author":"Lee"},{"key":"ref20","article-title":"D4RL: datasets for deep data-driven reinforcement learning","author":"Justin","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-017-02717-4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LED.2018.2856092"},{"key":"ref23","article-title":"Deep reinforcement learning with spiking q-learning","author":"Chen","year":"2022"},{"key":"ref24","article-title":"Randomized ensembled double q-learning: Learning fast without a model","volume-title":"proceedings of International Conference on Learning Representations","author":"Chen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20665"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00516"},{"key":"ref27","article-title":"SpikingJelly","author":"Fang","year":"2020"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650965.pdf?arnumber=10650965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T08:53:51Z","timestamp":1725958431000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650965\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650965","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}