{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:30:00Z","timestamp":1766068200076,"version":"build-2065373602"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T00:00:00Z","timestamp":1755388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T00:00:00Z","timestamp":1755388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100016311","name":"Arm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,17]]},"DOI":"10.1109\/case58245.2025.11164095","type":"proceedings-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:24:07Z","timestamp":1758648247000},"page":"1715-1721","source":"Crossref","is-referenced-by-count":1,"title":["Physical State Exploration for Reinforcement Learning from Scratch"],"prefix":"10.1109","author":[{"given":"Allison","family":"Pinosky","sequence":"first","affiliation":[{"name":"Northwestern University,Department of Mechanical Engineering,Chicago,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas A.","family":"Berrueta","sequence":"additional","affiliation":[{"name":"Northwestern University,Department of Mechanical Engineering,Chicago,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivia","family":"Li","sequence":"additional","affiliation":[{"name":"Northwestern University,Department of Mechanical Engineering,Chicago,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Todd D.","family":"Murphey","sequence":"additional","affiliation":[{"name":"Northwestern University,Department of Mechanical Engineering,Chicago,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CASE59546.2024.10711718"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49997.2022.9926540"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3185071"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref7","first-page":"1025","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Gupta"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812166"},{"article-title":"Don\u2019t start from scratch: Leveraging prior data to automate robotic reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Walke","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CASE59546.2024.10711622"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/science.1229163"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2851026"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"article-title":"A survey of exploration methods in reinforcement learning","year":"2021","author":"Amin","key":"ref15"},{"article-title":"On bonus based exploration methods in the arcade learning environment","volume-title":"International Conference on Learning Representations (ICLR)","author":"Taiga","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref18","article-title":"# exploration: A study of count-based exploration for deep reinforcement learning","volume":"30","author":"Tang","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning (ICML)","author":"Haarnoja","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3352580"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00829-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989545"},{"article-title":"Benchmarking reinforcement learning algorithms on real-world robots","volume-title":"Conference on Robot Learning (CoRL)","author":"Mahmood","key":"ref25"},{"article-title":"Benchmarking offline reinforcement learning on real-robot hardware","volume-title":"International Conference on Learning Representations (ICLR)","author":"G\u00fcrtler","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794390"},{"article-title":"Robel: Robotics benchmarks for learning with low-cost robots","volume-title":"Conference on Robot Learning (CoRL)","author":"Ahn","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650813"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801377"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1119\/1.10903"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981131"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611531"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9216782"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1177\/027836499000900208"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399617"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/a:1017936530646"},{"article-title":"Off-policy temporal-difference learning with function approximation","volume-title":"International Conference on Machine Learning (ICML)","author":"Precup","key":"ref38"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989179"}],"event":{"name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","start":{"date-parts":[[2025,8,17]]},"location":"Los Angeles, CA, USA","end":{"date-parts":[[2025,8,21]]}},"container-title":["2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11163731\/11163732\/11164095.pdf?arnumber=11164095","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T14:36:18Z","timestamp":1759242978000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11164095\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,17]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/case58245.2025.11164095","relation":{},"subject":[],"published":{"date-parts":[[2025,8,17]]}}}