{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T05:29:20Z","timestamp":1745645360570,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T00:00:00Z","timestamp":1694476800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T00:00:00Z","timestamp":1694476800000},"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":[[2023,9,12]]},"DOI":"10.1109\/etfa54631.2023.10275522","type":"proceedings-article","created":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T17:38:14Z","timestamp":1697132294000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Optimal set point generation based on deep reinforcement learning and transfer knowledge for Wastewater Treatment Plants"],"prefix":"10.1109","author":[{"given":"Oscar","family":"Aponte-Rengifo","sequence":"first","affiliation":[{"name":"University of Salamanca,Informatics and Automatics Department,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ram\u00f3n","family":"Vilanova","sequence":"additional","affiliation":[{"name":"Autonoma University of Barcelona,Telecommunications and Systems Department,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mario","family":"Francisco","sequence":"additional","affiliation":[{"name":"University of Salamanca,Informatics and Automatics Department,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pastora","family":"Vega","sequence":"additional","affiliation":[{"name":"University of Salamanca,Informatics and Automatics Department,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Silvana","family":"Revollar","sequence":"additional","affiliation":[{"name":"University of Salamanca,Informatics and Automatics Department,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.psep.2019.11.014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911372"},{"key":"ref34","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICSTCC50638.2020.9259637"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.envsoft.2017.11.023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/w13050612"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/su12030768"},{"key":"ref11","article-title":"Benchmark simulation model no. 1 (BSM1)","volume":"1","author":"alex","year":"2008","journal-title":"Report by the IWA Taskgroup on Benchmarking of Control Strategies for WWTPs"},{"key":"ref33","first-page":"17818","article-title":"The Role of Baselines in Policy Gradient Optimization","volume":"35","author":"mei","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2162401"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2958342"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref2"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"381","DOI":"10.21275\/ART20203995","article-title":"Machine learning algorithms-a review","volume":"9","author":"mahesh","year":"2020","journal-title":"International Journal of Science and Research (IJSR)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/app13042432"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.06.136"},{"key":"ref19","article-title":"Dynamic potential-based reward shaping","author":"devlin","year":"2012","journal-title":"ICAAMAS"},{"article-title":"Transfer learning in deep reinforcement learning: A survey","year":"2020","author":"zhu","key":"ref18"},{"key":"ref24","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"AISTATS"},{"key":"ref23","article-title":"Distilling policy distillation","author":"czarnecki","year":"2019","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28499-1_2"},{"key":"ref25","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","author":"gupta","year":"2017","journal-title":"ICLRE"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9628"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"article-title":"Representation matters: Offline pretraining for sequential decision making","year":"2021","author":"yang","key":"ref21"},{"article-title":"Pathnet: Evolution channels gradient descent in super neural networks","year":"2017","author":"fernando","key":"ref28"},{"article-title":"Progressive neural networks","year":"2016","author":"rusu","key":"ref27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph17010170"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.chemosphere.2021.130498"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2014.03.027"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3122802"},{"key":"ref4","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.envsoft.2003.03.005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1201\/9780203734209"}],"event":{"name":"2023 IEEE 28th International Conference on Emerging Technologies and Factory Automation (ETFA)","start":{"date-parts":[[2023,9,12]]},"location":"Sinaia, Romania","end":{"date-parts":[[2023,9,15]]}},"container-title":["2023 IEEE 28th International Conference on Emerging Technologies and Factory Automation (ETFA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10275065\/10275329\/10275522.pdf?arnumber=10275522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T19:03:34Z","timestamp":1730315014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10275522\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,12]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/etfa54631.2023.10275522","relation":{},"subject":[],"published":{"date-parts":[[2023,9,12]]}}}