{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:41:58Z","timestamp":1753602118452,"version":"3.37.3"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information & communications Technology Promotion","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003621","name":"Korea government","doi-asserted-by":"publisher","award":["2021-0-01381"],"award-info":[{"award-number":["2021-0-01381"]}],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information & communications Technology Planning & Evaluation"},{"DOI":"10.13039\/501100003621","name":"Korea government","doi-asserted-by":"publisher","award":["2022-0-00951"],"award-info":[{"award-number":["2022-0-00951"]}],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3182107","type":"journal-article","created":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T20:37:09Z","timestamp":1654893429000},"page":"64965-64975","source":"Crossref","is-referenced-by-count":4,"title":["Utilizing Skipped Frames in Action Repeats for Improving Sample Efficiency in Reinforcement Learning"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9488-7463","authenticated-orcid":false,"given":"Tung M.","family":"Luu","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}]},{"given":"Thanh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}]},{"given":"Thang","family":"Vu","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0756-7179","authenticated-orcid":false,"given":"Chang D.","family":"Yoo","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5092","article-title":"Learning to poke by poking: Experiential learning of intuitive physics","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Agrawal"},{"key":"ref2","article-title":"Solving Rubik\u2019s cube with a robot hand","author":"Akkaya","year":"2019","journal-title":"arXiv:1910.07113"},{"key":"ref3","first-page":"5048","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Andrychowicz"},{"key":"ref4","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref5","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Bellemare"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1613\/jair.3912"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1609\/aaai.v30i1.10303"},{"key":"ref8","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"volume-title":"Proc. AAAI Workshop, Learn. Gen. Competency Video Games","author":"Braylan","article-title":"Frame skip is a powerful parameter for learning to play atari","key":"ref9"},{"key":"ref10","first-page":"172","article-title":"Action-gap phenomenon in reinforcement learning","author":"Farahmand","year":"2011","journal-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref11","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Fujimoto"},{"key":"ref12","article-title":"World models","author":"Ha","year":"2018","journal-title":"arXiv:1803.10122"},{"key":"ref13","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. (ICML)","author":"Haarnoja"},{"volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hafner","article-title":"Dream to control: Learning behaviors by latent imagination","key":"ref14"},{"key":"ref15","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Hafner"},{"volume-title":"Proc. Deep Reinforcement Learn. Workshop","author":"Hashimoto","article-title":"Utilizing skipped frames in action repeats via pseudo-actions","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref18","article-title":"On inductive biases in deep reinforcement learning","author":"Hessel","year":"2019","journal-title":"arXiv:1907.02908"},{"volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Jaderberg","article-title":"Reinforcement learning with unsupervised auxiliary tasks","key":"ref19"},{"volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kaiser","article-title":"Model based reinforcement learning for atari","key":"ref20"},{"key":"ref21","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Proc. Conf. Robot. Learn. (CoRL)","author":"Kalashnikov"},{"key":"ref22","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Diederik Kingma"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1609\/aaai.v31i1.10918"},{"key":"ref24","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Laskin"},{"key":"ref25","first-page":"741","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","author":"Lee","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref26","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Lillicrap"},{"key":"ref27","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Mnih"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1038\/nature14236"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1007\/11552246_35"},{"volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Paster","article-title":"Planning from pixels using inverse dynamics models","key":"ref30"},{"key":"ref31","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Schulman"},{"key":"ref32","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Sharma","article-title":"Learning to repeat: Fine grained action repetition for deep reinforcement learning","key":"ref33"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1038\/nature16961"},{"key":"ref35","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","author":"Silver","year":"2017","journal-title":"arXiv:1712.01815"},{"key":"ref36","first-page":"5639","article-title":"CURL: Contrastive unsupervised representations for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Srinivas"},{"key":"ref37","first-page":"9870","article-title":"Decoupling representation learning from reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Stooke"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/TNN.1998.712192"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1016\/j.simpa.2020.100022"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref41","first-page":"4294","article-title":"Learning values across many orders of magnitude","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Hasselt"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref43","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Wang"},{"volume-title":"Proc. Conf. Robot. Learn. (CoRL)","author":"Yan","article-title":"Learning predictive representations for deformable objects using contrastive estimation","key":"ref44"},{"volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Yarats","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","key":"ref45"},{"year":"2010","author":"Ziebart","article-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","key":"ref46"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09793636.pdf?arnumber=9793636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T02:01:29Z","timestamp":1706752889000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9793636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3182107","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2022]]}}}