{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T06:11:29Z","timestamp":1760422289244,"version":"build-2065373602"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"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":[[2025,5,23]]},"DOI":"10.1109\/icmlt65785.2025.11193222","type":"proceedings-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T17:39:05Z","timestamp":1760377145000},"page":"135-140","source":"Crossref","is-referenced-by-count":0,"title":["An Adaptive Policy Switching Method for Episodic Cumulative Reward in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Natsuhiko","family":"Sato","sequence":"first","affiliation":[{"name":"NEC Corporation,Visual Intelligence Research Laboratories,Kanagawa,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Yoshida","sequence":"additional","affiliation":[{"name":"NEC Corporation,Visual Intelligence Research Laboratories,Kanagawa,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802813"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2932789"},{"key":"ref3","article-title":"Simulator-based reinforcement learning for data center cooling optimization \u2014 engineering.fb.com"},{"key":"ref4","first-page":"3818","article-title":"Data center cooling using model-predictive control","volume-title":"Proceedings of the Thirty-second Conference on Neural Information Processing Systems (NeurIPS-18)","author":"Lazic"},{"article-title":"Model-free risk-sensitive reinforcement learning","year":"2021","author":"Del\u00e9tang","key":"ref5"},{"issue":"9","key":"ref6","first-page":"7899","article-title":"Variance penalized on-policy and off-policy actor-critic","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"35","author":"Jain"},{"issue":"167","key":"ref7","first-page":"1","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume-title":"Journal of Machine Learning Research","volume":"18","author":"Chow","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341948"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/SICE56594.2022.9905836"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-022-09552-y"},{"key":"ref11","first-page":"6131","article-title":"Sunrise: A simple unified framework for ensemble learning in deep reinforcement learning","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"139","author":"Lee"},{"key":"ref12","article-title":"A tutorial on stochastic programming","volume-title":"Manuscript","volume":"17","author":"Shapiro","year":"2007"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2000.038"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/24709360.2017.1396742"}],"event":{"name":"2025 10th International Conference on Machine Learning Technologies (ICMLT)","start":{"date-parts":[[2025,5,23]]},"location":"Helsinki, Finland","end":{"date-parts":[[2025,5,25]]}},"container-title":["2025 10th International Conference on Machine Learning Technologies (ICMLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11192828\/11192850\/11193222.pdf?arnumber=11193222","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T05:32:01Z","timestamp":1760419921000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11193222\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,23]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/icmlt65785.2025.11193222","relation":{},"subject":[],"published":{"date-parts":[[2025,5,23]]}}}