{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T01:22:25Z","timestamp":1773451345338,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"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":[[2024,9,2]]},"DOI":"10.1109\/mesa61532.2024.10704825","type":"proceedings-article","created":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T17:45:08Z","timestamp":1728495908000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Solving the Wire Loop Game with a reinforcement-learning controller based on haptic feedback"],"prefix":"10.1109","author":[{"given":"Lorenzo","family":"Mazzotti","sequence":"first","affiliation":[{"name":"University of Bologna,Dept. of Industrial Engineering,Bologna,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michele","family":"Angelini","sequence":"additional","affiliation":[{"name":"University of Bologna,Dept. of Industrial Engineering,Bologna,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Carricato","sequence":"additional","affiliation":[{"name":"University of Bologna,Dept. of Industrial Engineering,Bologna,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s12053-020-09900-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2015.03.002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/vehicles3030027"},{"key":"ref4","volume-title":"Artificial intelligence: A modern approach","author":"Russell","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/AGENTS.2018.8460004"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROSE56499.2022.9977430"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA57826.2023.10215710"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3312237"},{"key":"ref10","article-title":"Racing towards reinforcement learning based control of an autonomous formula SAE car","volume-title":"Australasian Conference on Robotics and Automation, ACRA","author":"Salvaji"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/ICNSC48988.2020.9238090","article-title":"Robot navigation with map-based deep reinforcement learning","author":"Chen","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICIINFS.2017.8300386"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/AIM52237.2022.9863259"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IRC55401.2022.00058"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3300230"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA54519.2022.9856351"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2018.03.067"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICARSC55462.2022.9784814"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206110"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3254860"},{"key":"ref21","article-title":"Reducing the barrier to entry of complex robotic software: a MoveIt! case study","author":"Coleman","year":"2014"},{"key":"ref22","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref23","article-title":"Implementation matters in deep policy gradients: A case study on PPO and TRPO","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Engstrom"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3124466"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR.2018.8468611"},{"key":"ref26","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref27","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016"},{"key":"ref28","article-title":"A2C is a special case of PPO","author":"Huang","year":"2022"}],"event":{"name":"2024 20th IEEE\/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","location":"Genova, Italy","start":{"date-parts":[[2024,9,2]]},"end":{"date-parts":[[2024,9,4]]}},"container-title":["2024 20th IEEE\/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10704794\/10704793\/10704825.pdf?arnumber=10704825","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T11:29:09Z","timestamp":1728559749000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10704825\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,2]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/mesa61532.2024.10704825","relation":{},"subject":[],"published":{"date-parts":[[2024,9,2]]}}}