{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:46:30Z","timestamp":1755798390382,"version":"3.44.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"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":[[2025,9,14]]},"DOI":"10.1109\/icip55913.2025.11084649","type":"proceedings-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:41:38Z","timestamp":1755546098000},"page":"1774-1779","source":"Crossref","is-referenced-by-count":0,"title":["Time-Efficient Uncertainty Estimation Based on Target Networks in Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xionglue","family":"Li","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),School of Computer Science and Technology,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongguang","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Aerospace Institute for Metrology and Measurement Technology,Key Laboratory of Artificial Intelligence Measurement and Standards for State Market Regulation,Beijing,China,100076"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijuan","family":"Sun","sequence":"additional","affiliation":[{"name":"Beijing Aerospace Institute for Metrology and Measurement Technology,Key Laboratory of Artificial Intelligence Measurement and Standards for State Market Regulation,Beijing,China,100076"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongyong","family":"Chen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),School of Computer Science and Technology,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"article-title":"Drivergym: Democratising reinforcement learning for autonomous driving","year":"2021","author":"Kothari","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/robotics10010022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.05.008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v18i1.21959"},{"article-title":"Deep exploration via bootstrapped dqn","volume-title":"Proceedings of NeurIPS","author":"Osband","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref10","first-page":"8454","article-title":"Ensemble bootstrapping for q-learning","volume-title":"Proceedings of ICML","author":"Peer"},{"article-title":"Efficient exploration with double uncertain value networks","year":"2017","author":"Moerland","key":"ref11"},{"article-title":"Estimating risk and uncertainty in deep reinforcement learning","year":"2019","author":"Clements","key":"ref12"},{"article-title":"Bayesian policy optimization for model uncertainty","year":"2018","author":"Lee","key":"ref13"},{"article-title":"Sample efficient deep reinforcement learning via uncertainty estimation","year":"2022","author":"Mai","key":"ref14"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref15"},{"key":"ref16","article-title":"Fully parameterized quantile function for distributional reinforcement learning","volume-title":"Proceedings of NeurIPS","volume":"32","author":"Yang"},{"key":"ref17","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"Proceedings of ICML","author":"Dabney"},{"key":"ref18","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proceedings of ICML","author":"Bellemare"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref20","first-page":"1183","article-title":"Deep bayesian active learning with image data","volume-title":"Proceedings of ICML","author":"Gal"},{"article-title":"Minatar: An atari-inspired testbed for thorough and reproducible reinforcement learning experiments","year":"2019","author":"Young","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5699"},{"key":"ref23","first-page":"6","article-title":"A method for stochastic optimization","volume-title":"Proceedings of ICLR","volume":"5","author":"Kinga"}],"event":{"name":"2025 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2025,9,14]]},"location":"Anchorage, AK, USA","end":{"date-parts":[[2025,9,17]]}},"container-title":["2025 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11084272\/11083968\/11084649.pdf?arnumber=11084649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T05:01:58Z","timestamp":1755579718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11084649\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icip55913.2025.11084649","relation":{},"subject":[],"published":{"date-parts":[[2025,9,14]]}}}