{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T09:13:12Z","timestamp":1778663592415,"version":"3.51.4"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tsmc.2024.3505613","type":"journal-article","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T19:12:53Z","timestamp":1733339573000},"page":"1425-1438","source":"Crossref","is-referenced-by-count":5,"title":["On the Effectiveness of Regularization Methods for Soft Actor-Critic in Discrete-Action Domains"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4948-6713","authenticated-orcid":false,"given":"Bang Giang","family":"Le","sequence":"first","affiliation":[{"name":"Human-Machine Interaction Laboratory, VNU University of Engineering and Technology, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8058-5915","authenticated-orcid":false,"given":"Viet Cuong","family":"Ta","sequence":"additional","affiliation":[{"name":"Human-Machine Interaction Laboratory, VNU University of Engineering and Technology, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1861","article-title":"Soft actor\u2013critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"issue":"1","key":"ref2","first-page":"12348","article-title":"Stable-Baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"issue":"267","key":"ref3","first-page":"1","article-title":"Tianshou: A highly modularized deep reinforcement learning library","volume":"23","author":"Weng","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref4","first-page":"1","article-title":"Gradient estimation using stochastic computation graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Schulman"},{"key":"ref5","article-title":"Combining policy gradient and Q-learning","author":"O\u2019Donoghue","year":"2016","journal-title":"arXiv:1611.01626"},{"key":"ref6","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref7","first-page":"1587","article-title":"Addressing function approximation error in actor\u2013critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref9","first-page":"1","article-title":"Soft Q-learning with mutual-information regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Grau-Moya"},{"key":"ref10","first-page":"4018","article-title":"Diversity actor\u2013critic: Sample-aware entropy regularization for sample-efficient exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Han"},{"key":"ref11","first-page":"1","article-title":"Adversarially guided actor\u2013critic","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Flet-Berliac"},{"key":"ref12","article-title":"Soft actor\u2013critic for discrete action settings","author":"Christodoulou","year":"2019","journal-title":"arXiv:1910.07207"},{"key":"ref13","article-title":"Target entropy annealing for discrete soft actor\u2013critic","author":"Xu","year":"2021","journal-title":"arXiv:2112.02852"},{"key":"ref14","article-title":"Revisiting discrete soft actor\u2013critic","author":"Zhou","year":"2022","journal-title":"arXiv:2209.10081"},{"key":"ref15","volume-title":"Minimalistic gridworld environment for OpenAI gym","author":"Chevalier-Boisvert","year":"2018"},{"key":"ref16","first-page":"1","article-title":"Bridging the gap between value and policy based reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Nachum"},{"key":"ref17","article-title":"Taming the noise in reinforcement learning via soft updates","author":"Fox","year":"2015","journal-title":"arXiv:1512.08562"},{"key":"ref18","article-title":"Equivalence between policy gradients and soft Q-learning","author":"Schulman","year":"2017","journal-title":"arXiv:1704.06440"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2014.2387822"},{"key":"ref20","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref21","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref22","article-title":"Information asymmetry in KL-regularized RL","author":"Galashov","year":"2019","journal-title":"arXiv:1905.01240"},{"key":"ref23","first-page":"1","article-title":"Distral: Robust multitask reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Teh"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref25","article-title":"Single-timescale actor\u2013critic provably finds globally optimal policy","author":"Fu","year":"2020","journal-title":"arXiv:2008.00483"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5699"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref29","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref30","article-title":"Sample efficient actor\u2013critic with experience replay","author":"Wang","year":"2016","journal-title":"arXiv:1611.01224"},{"key":"ref31","first-page":"1","article-title":"Scalable and sample-efficient multiagent imitation learning","volume-title":"Proc. Workshop 34th AAAI Conf. Artif. Intell. Safety","author":"Jeon"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3274908"},{"key":"ref33","first-page":"2681","article-title":"Provably efficient maximum entropy exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hazan"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref35","first-page":"1","article-title":"Better exploration with optimistic actor critic","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ciosek"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800085"},{"key":"ref37","first-page":"2160","article-title":"A theory of regularized Markov decision processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Geist"},{"key":"ref38","first-page":"1","article-title":"A regularized approach to sparse optimal policy in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213566"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3098985"},{"key":"ref41","first-page":"151","article-title":"Understanding the impact of entropy on policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ahmed"},{"key":"ref42","article-title":"Trust-PCL: An off-policy trust region method for continuous control","author":"Nachum","year":"2017","journal-title":"arXiv:1707.01891"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3044196"},{"key":"ref44","article-title":"Dropout Q-functions for doubly efficient reinforcement learning","author":"Hiraoka","year":"2021","journal-title":"arXiv:2110.02034"},{"key":"ref45","first-page":"1","article-title":"Sample-efficient reinforcement learning by breaking the replay ratio barrier","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"D\u2019Oro"},{"key":"ref46","first-page":"1","article-title":"CrossQ: Batch normalization in deep reinforcement learning for greater sample efficiency and simplicity","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bhatt"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/10843065\/10777063.pdf?arnumber=10777063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:57:25Z","timestamp":1737399445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10777063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":46,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2024.3505613","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}