{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T22:24:09Z","timestamp":1725747849894},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T00:00:00Z","timestamp":1672963200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T00:00:00Z","timestamp":1672963200000},"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":[[2023,1,6]]},"DOI":"10.1109\/icce56470.2023.10043558","type":"proceedings-article","created":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T18:57:49Z","timestamp":1676660269000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["End to End Optimized Tiny Learning for Repositionable Walls in Maze Topologies"],"prefix":"10.1109","author":[{"given":"Danilo","family":"Pau","sequence":"first","affiliation":[{"name":"STMicroelectronics,System Research and Applications,Agrate Brianza,Italy"}]},{"given":"Stefano","family":"Colella","sequence":"additional","affiliation":[{"name":"Politecnico di Milano, STMicroelectronics,System Research and Applications,Agrate Brianza,Italy"}]},{"given":"Claudio","family":"Marchisio","sequence":"additional","affiliation":[{"name":"STMicroelectronics,System Research and Applications,Agrate Brianza,Italy"}]}],"member":"263","reference":[{"key":"ref1","first-page":"17","article-title":"Limits of end-to-end learning","volume-title":"Asian conference on machine learning","author":"Glasmachers","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref3","article-title":"Playing Atari with Deep Reinforcement Learning","author":"Mnih","year":"2013","journal-title":"arXiv"},{"volume-title":"Learning from delayed rewards","year":"1989","author":"Watkins","key":"ref4"},{"key":"ref5","article-title":"Dueling Network Architectures for Deep Reinforcement Learning","author":"Wang","year":"2015","journal-title":"arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref7","article-title":"Prioritized Experience Replay","author":"Schaul","year":"2015","journal-title":"arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref9","article-title":"Proximal Policy Optimization Algorithms","author":"Schulman","year":"2017","journal-title":"arXiv"},{"key":"ref10","article-title":"Asynchronous Methods for Deep Reinforcement Learning","author":"Mnih","year":"2016","journal-title":"arXiv"},{"key":"ref11","article-title":"Trust Region Policy Optimization","author":"Schulman","year":"2015","journal-title":"arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/PHM-Jinan48558.2020.00012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3026638"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.01.054"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11645"},{"key":"ref17","article-title":"Resource Efficient Deep Reinforcement Learning for Acutely Constrained TinyML Devices","volume-title":"Research Symposium on Tiny Machine Learning","author":"Svoboda","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3322645.3322693"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561590"},{"key":"ref20","article-title":"OpenAI Gym","author":"Brockman","year":"2016","journal-title":"arXiv"},{"issue":"22","key":"ref21","first-page":"1","article-title":"Stable-Baselines3: Reliable Reinforcement Learning","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","article-title":"Dealing with Sparse Rewards in Reinforcement Learning","author":"Hare","year":"2019","journal-title":"arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"}],"event":{"name":"2023 IEEE International Conference on Consumer Electronics (ICCE)","start":{"date-parts":[[2023,1,6]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2023,1,8]]}},"container-title":["2023 IEEE International Conference on Consumer Electronics (ICCE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10043349\/10043179\/10043558.pdf?arnumber=10043558","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T05:27:21Z","timestamp":1712899641000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10043558\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icce56470.2023.10043558","relation":{},"subject":[],"published":{"date-parts":[[2023,1,6]]}}}