{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T00:56:05Z","timestamp":1769129765311,"version":"3.49.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"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":[[2025,12,2]]},"DOI":"10.1109\/icar65334.2025.11338734","type":"proceedings-article","created":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T21:06:47Z","timestamp":1769029607000},"page":"59-66","source":"Crossref","is-referenced-by-count":0,"title":["Meta Reinforcement Learning Applied to Quadrupedal Robots for Blind Locomotion and Fast Adaptation on Unknown Terrains"],"prefix":"10.1109","author":[{"given":"Pedro Leon F. C.","family":"Bazan","sequence":"first","affiliation":[{"name":"Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio),Robotics Lab (LabRob),Department of Mechanical Engineering,Brazil"}]},{"given":"Wouter","family":"Caarls","sequence":"additional","affiliation":[{"name":"PUC-Rio,Intelligent Control Lab (LCI),Department of Electrical Engineering,Brazil"}]},{"given":"Vivian S.","family":"Medeiros","sequence":"additional","affiliation":[{"name":"University of São Paulo (USP),Legged Robotics Group, São Carlos School of Engineering (EESC)"}]},{"given":"Marco A.","family":"Meggiolaro","sequence":"additional","affiliation":[{"name":"Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio),Robotics Lab (LabRob),Department of Mechanical Engineering,Brazil"}]}],"member":"263","reference":[{"key":"ref1","author":"van Marum","year":"2023","journal-title":"Learning perceptive bipedal locomotion over irregular terrain"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/s22145217"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CAC48633.2019.8997036"},{"key":"ref4","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460731"},{"key":"ref6","first-page":"1","article-title":"Analysis and comparison of slip detection methods for quadruped robots","volume-title":"Proc. LARS","author":"de Carvalho"},{"key":"ref7","author":"Beck","year":"2023","journal-title":"A survey of meta-reinforcement learning"},{"key":"ref8","author":"Duan","year":"2016","journal-title":"Rl 2: Fast reinforcement learning via slow reinforcement learning"},{"key":"ref9","author":"Schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SISY62279.2024.10737619"},{"key":"ref11","author":"Kang","year":"2022","journal-title":"Nonlinear model predictive control for quadrupedal locomotion using second-order sensitivity analysis"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-021-01418-x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICMERR64601.2025.10949908"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375154"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801341"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/biomimetics9010037"},{"key":"ref17","first-page":"arXiv","author":"Di Giuro","year":"2024","journal-title":"Meta-reinforcement learning for universal quadrupedal locomotion control"},{"key":"ref18","author":"Zhao","year":"2024","journal-title":"Zsl-rppo: Zero-shot learning for quadrupedal locomotion in challenging terrains using recurrent proximal policy optimization"},{"key":"ref19","author":"Kuzhamuratov","year":"2021","journal-title":"Adaptation of quadruped robot locomotion with meta-learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3211785"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2026.3653774"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981660"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561313"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161144"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-60801-3_27"},{"key":"ref27","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"NIPS 2014 Workshop on Deep Learning, December 2014","author":"Chung"},{"key":"ref28","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Rudin"},{"key":"ref29","volume-title":"Deep learning","author":"Goodfellow","year":"2016"}],"event":{"name":"2025 IEEE International Conference on Advanced Robotics (ICAR)","location":"San Juan, Argentina","start":{"date-parts":[[2025,12,2]]},"end":{"date-parts":[[2025,12,5]]}},"container-title":["2025 IEEE International Conference on Advanced Robotics (ICAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11338521\/11338600\/11338734.pdf?arnumber=11338734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T08:23:39Z","timestamp":1769070219000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11338734\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icar65334.2025.11338734","relation":{},"subject":[],"published":{"date-parts":[[2025,12,2]]}}}