{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T04:38:32Z","timestamp":1754109512554,"version":"3.28.2"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T00:00:00Z","timestamp":1724803200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T00:00:00Z","timestamp":1724803200000},"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":[[2024,8,28]]},"DOI":"10.1109\/case59546.2024.10711561","type":"proceedings-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T17:40:16Z","timestamp":1729705216000},"page":"1028-1033","source":"Crossref","is-referenced-by-count":4,"title":["Improving Generalization in Aerial and Terrestrial Mobile Robots Control Through Delayed Policy Learning"],"prefix":"10.1109","author":[{"given":"Ricardo B.","family":"Grando","sequence":"first","affiliation":[{"name":"Universidad Tecnologica del Uruguay - UTEC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raul","family":"Steinmetz","sequence":"additional","affiliation":[{"name":"Universidade Federal de Santa Maria - UFSM"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Victor A.","family":"Kich","sequence":"additional","affiliation":[{"name":"University of Tsukuba"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alisson H.","family":"Kolling","sequence":"additional","affiliation":[{"name":"Universidade Federal de Rio Grande - FURG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pablo M.","family":"Furik","sequence":"additional","affiliation":[{"name":"Universidad Tecnologica del Uruguay - UTEC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junior C.","family":"de Jesus","sequence":"additional","affiliation":[{"name":"Universidade Federal de Rio Grande - FURG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bruna V.","family":"Guterres","sequence":"additional","affiliation":[{"name":"Universidad Tecnologica del Uruguay - UTEC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel T.","family":"Gamarra","sequence":"additional","affiliation":[{"name":"Universidade Federal de Santa Maria - UFSM"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rodrigo S.","family":"Guerra","sequence":"additional","affiliation":[{"name":"Universidade Federal de Rio Grande - FURG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L. J.","family":"Drews","sequence":"additional","affiliation":[{"name":"Universidade Federal de Rio Grande - FURG"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","first-page":"229","article-title":"Reinforcement learning: An introduction","volume":"17","author":"Sutton","year":"1999","journal-title":"Robotica"},{"volume-title":"Grokking deep reinforcement learning.","year":"2020","author":"Morales","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","first-page":"1","article-title":"Deep reinforcement learning for robotic manipulation","volume":"1","author":"Gu","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"article-title":"Assessing generalization in deep reinforcement learning","year":"2018","author":"Packer","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LARS\/SBR\/WRE56824.2022.9995792"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LARS\/SBR\/WRE56824.2022.9995830"},{"article-title":"Sensitivity and generalization in neural networks: an empirical study","year":"2018","author":"Novak","key":"ref9"},{"issue":"1","key":"ref10","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"The journal of machine learning research"},{"key":"ref11","article-title":"Dropout training as adaptive regularization","volume":"26","author":"Wager","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"ref13","article-title":"Self-normalizing neural networks","volume":"30","author":"Klambauer","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504"},{"article-title":"A study on overfitting in deep reinforcement learning","year":"2018","author":"Zhang","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"ref17","first-page":"7968","article-title":"Improving generalization in reinforcement learning with mixture regularization","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018","journal-title":"ICML"},{"key":"ref19","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume-title":"IEEE ICML.","author":"Cobbe"},{"article-title":"Generalization and regularization in dqn","year":"2018","author":"Farebrother","key":"ref20"},{"article-title":"Network randomization: A simple technique for generalization in deep reinforcement learning","year":"2019","author":"Lee","key":"ref21"},{"article-title":"Illuminating generalization in deep reinforcement learning through procedural level generation","year":"2018","author":"Justesen","key":"ref22"},{"article-title":"Automatic data augmentation for generalization in deep reinforcement learning","year":"2020","author":"Raileanu","key":"ref23"},{"key":"ref24","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2016","journal-title":"ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/s20195493"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-021-01568-y"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LARS\/SBR\/WRE56824.2022.9995813"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA54519.2022.9856399"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LARS\/SBR\/WRE59448.2023.10333008"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LARS\/SBR\/WRE59448.2023.10333051"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5220\/0007724500590066"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561188"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LARS\/SBR\/WRE51543.2020.9307110"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR46387.2019.8981667"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982161"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26054-9_23"}],"event":{"name":"2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)","start":{"date-parts":[[2024,8,28]]},"location":"Bari, Italy","end":{"date-parts":[[2024,9,1]]}},"container-title":["2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10711304\/10711288\/10711561.pdf?arnumber=10711561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T01:20:32Z","timestamp":1732670432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10711561\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,28]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/case59546.2024.10711561","relation":{},"subject":[],"published":{"date-parts":[[2024,8,28]]}}}