{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:07:51Z","timestamp":1766138871844,"version":"3.28.0"},"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650439","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["Consolidated Adaptive T-soft Update for Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Taisuke","family":"Kobayashi","sequence":"first","affiliation":[{"name":"The Graduate University for Advanced Studies (SOKENDAI),National Institute of Informatics (NII),Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2412554"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202100038"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2426451"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21887"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.11.004"},{"issue":"30","key":"ref6","first-page":"1","article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms","volume":"22","author":"Kroemer","year":"2021","journal-title":"Journal of Machine Learning Research"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref9","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":"ref10","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981812"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.12.023"},{"key":"ref14","first-page":"12 621","article-title":"Breaking the deadly triad with a target network","volume-title":"International Conference on Machine Learning","author":"Zhang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/22m1499261"},{"key":"ref16","first-page":"991","article-title":"Analysis of a target-based actor-critic algorithm with linear function approximation","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Barakat"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/379"},{"article-title":"Beyond target networks: Improving deep q-learning with functional regularization","year":"2021","author":"Pich\u00e9","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126692"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref22","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume-title":"International Conference on Machine Learning","author":"Zenke"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-019-01510-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2921598"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3125000"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.010"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.04.021"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","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\/10650439.pdf?arnumber=10650439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:25:56Z","timestamp":1725945956000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650439","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}