{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T09:00:36Z","timestamp":1767085236430,"version":"3.30.2"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"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":[[2024,10,17]]},"DOI":"10.1109\/iccp63557.2024.10792984","type":"proceedings-article","created":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T19:09:09Z","timestamp":1734462549000},"page":"1-7","source":"Crossref","is-referenced-by-count":3,"title":["Policy Transfer with Maximum Entropy Deep Reinforcement Learning for Real Cart-Pole Control"],"prefix":"10.1109","author":[{"given":"Tudor-Andrei","family":"Paleu","sequence":"first","affiliation":[{"name":"Gheorghe Asachi Technical University of Iasi,Department of Automatic Control and Applied Informatics,Iasi,Romania,700050"}]},{"given":"Adrian","family":"Burlacu","sequence":"additional","affiliation":[{"name":"Gheorghe Asachi Technical University of Iasi,Department of Automatic Control and Applied Informatics,Iasi,Romania,700050"}]},{"given":"Carlos","family":"Pascal","sequence":"additional","affiliation":[{"name":"Gheorghe Asachi Technical University of Iasi,Department of Automatic Control and Applied Informatics,Iasi,Romania,700050"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2966414"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2905621"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/app10249013"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/00202940211000380"},{"key":"ref11","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","volume-title":"Proceedings of the 28th International Conference on Machine Learning","author":"Deisenroth","year":"2011"},{"key":"ref12","article-title":"Lyapunov design for robust and efficient robotic reinforcement learning","author":"Westenbroek","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.011"},{"key":"ref14","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"International Conference on Machine Learning","author":"Haarnoja","year":"2017"},{"key":"ref15","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593722"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref18","article-title":"OpenAI Gym","author":"Brockman","year":"2016","journal-title":"arXiv preprint"},{"volume-title":"Inverted Pendulum Linear System (AA092.001.01)","year":"2022","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191071"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICSTCC59206.2023.10308431"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2022.799893"},{"key":"ref23","article-title":"Solving Rubik\u2019s Cube with a robot hand","author":"Akkaya","year":"2019","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Domain Randomization via Entropy Maximization","author":"Tiboni","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE 20th International Conference on Intelligent Computer Communication and Processing (ICCP)","start":{"date-parts":[[2024,10,17]]},"location":"Cluj-Napoca, Romania","end":{"date-parts":[[2024,10,19]]}},"container-title":["2024 IEEE 20th International Conference on Intelligent Computer Communication and Processing (ICCP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10792975\/10792923\/10792984.pdf?arnumber=10792984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T08:09:09Z","timestamp":1734509349000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10792984\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,17]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iccp63557.2024.10792984","relation":{},"subject":[],"published":{"date-parts":[[2024,10,17]]}}}