{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T06:46:11Z","timestamp":1763621171215,"version":"3.45.0"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3630331","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T18:11:21Z","timestamp":1762539081000},"page":"193878-193892","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced Multi-Critic Deep Reinforcement Learning for Channel Estimation in 6G N2V or I2V Communications"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0207-3583","authenticated-orcid":false,"given":"P.","family":"Mithillesh Kumar","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Bengaluru, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6147-7142","authenticated-orcid":false,"given":"M.","family":"Supriya","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Bengaluru, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3239220"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS54207.2022.9789886"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24425\/ijet.2022.139861"},{"key":"ref4","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016","journal-title":"arXiv:1602.01783"},{"key":"ref5","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"article-title":"Spinning up in deep reinforcement learning","year":"2018","author":"Achiam","key":"ref6"},{"article-title":"Multi-critic actor learning: Teaching RL policies to act with style","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mysore","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps56602.2022.10008713"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2023.3300962"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MysuruCon59703.2023.10396936"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-2821-5_7"},{"key":"ref14","first-page":"1","article-title":"Throughput analysis with effect of dimensionality reduction on 5G dataset using machine learning and deep learning models","volume-title":"Proc. Int. Conf. Ind. 4.0 Technol. (I4Tech)","author":"Kumar"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICESC57686.2023.10193024"},{"key":"ref16","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref17","article-title":"Trust region policy optimization","author":"Schulman","year":"2015","journal-title":"arXiv:1502.05477"},{"key":"ref18","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref19","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref20","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref21","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yang"},{"key":"ref22","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sodhani"},{"key":"ref23","first-page":"166","article-title":"Modular multitask reinforcement learning with policy sketches","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Andreas"},{"article-title":"Distral: Robust multitask reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Teh","key":"ref24"},{"key":"ref25","article-title":"Policy distillation","author":"Rusu","year":"2015","journal-title":"arXiv:1511.06295"},{"key":"ref26","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arXiv:1606.04671"},{"key":"ref27","article-title":"Learning to run with actor-critic ensemble","author":"Huang","year":"2017","journal-title":"arXiv:1712.08987"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/461"},{"key":"ref29","article-title":"DiGrad: Multi-task reinforcement learning with shared actions","author":"Dewangan","year":"2018","journal-title":"arXiv:1802.10463"},{"key":"ref30","article-title":"Gotta learn fast: A new benchmark for generalization in RL","author":"Nichol","year":"2018","journal-title":"arXiv:1804.03720"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref32","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Yu"},{"key":"ref33","article-title":"A closer look at deep policy gradients","author":"Ilyas","year":"2018","journal-title":"arXiv:1811.02553"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619008"},{"article-title":"What matters for on-policy deep actor-critic methods? a large-scale study","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Andrychowicz","key":"ref35"},{"key":"ref36","article-title":"Sharing knowledge in multi-task deep reinforcement learning","author":"D\u2019Eramo","year":"2024","journal-title":"arXiv:2401.09561"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMLCN.2023.3278232"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3272348"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3515075"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11232479.pdf?arnumber=11232479","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T06:07:37Z","timestamp":1763618857000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11232479\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3630331","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}