{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T10:04:54Z","timestamp":1766484294641,"version":"3.32.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801966","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"685-692","source":"Crossref","is-referenced-by-count":1,"title":["Learning When to Stop: Efficient Active Tactile Perception with Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Christopher","family":"Niemann","sequence":"first","affiliation":[{"name":"Bielefeld University,CoR-Lab, CITEC,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Leins","sequence":"additional","affiliation":[{"name":"Bielefeld University,Machine Learning Group, CITEC,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Lach","sequence":"additional","affiliation":[{"name":"CSIC-UPC,Institut de Robòtica i Informàtica Industrial"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Haschke","sequence":"additional","affiliation":[{"name":"Bielefeld University,Social Cognitive Systems Group, CITEC,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2017.11.002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.10.114"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2012.00004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630996"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9707-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3334971"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0226880"},{"author":"Mnih","key":"ref8","article-title":"Recurrent Models of Visual Attention"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WHC.2011.5945509"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3758\/bf03208368"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992696"},{"key":"ref12","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Advances in Neural Information Processing Systems","volume":"12","author":"Sutton","year":"1999"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref13"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings","author":"Schulman","key":"ref14"},{"article-title":"Continuous-discrete reinforcement learning for hybrid control in robotics","year":"2020","author":"Neunert","key":"ref15"},{"article-title":"Proximal Policy Optimization Algorithms","year":"2017","author":"Schulman","key":"ref16"},{"article-title":"Trust Region Policy Optimization","year":"2017","author":"Schulman","key":"ref17"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2021","author":"Dosovitskiy","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"article-title":"More Accurate Tactile Sensor Simulation with Hydroelastic Contacts in MuJoCo","volume-title":"IROS 2023 Workshop on Leveraging Models for Contact-Rich Manipulation","author":"Leins","key":"ref20"},{"article-title":"Curved Tactile Sensor Simulation with Hydroelastic Contacts in MuJoCo","volume-title":"NeurIPS 2023 Workshop on Touch Processing: a new Sensing Modality for AI","author":"Patzelt","key":"ref21"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801966.pdf?arnumber=10801966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:16:05Z","timestamp":1735197365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801966\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801966","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}