{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T18:40:20Z","timestamp":1777315220600,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247281","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"11669-11676","source":"Crossref","is-referenced-by-count":3,"title":["TAR: Teacher-Aligned Representations via Contrastive Learning for Quadrupedal Locomotion"],"prefix":"10.1109","author":[{"given":"Amr","family":"Mousa","sequence":"first","affiliation":[{"name":"University of Manchester,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neil","family":"Karavis","sequence":"additional","affiliation":[{"name":"BAE Systems,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michele","family":"Caprio","sequence":"additional","affiliation":[{"name":"University of Manchester,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Pan","sequence":"additional","affiliation":[{"name":"University of Manchester,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Allmendinger","sequence":"additional","affiliation":[{"name":"University of Manchester,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2024.3400935"},{"key":"ref5","doi-asserted-by":"crossref","article-title":"Pa-loco: Learning perturbation-adaptive locomotion for quadruped robots","author":"Xiao","DOI":"10.1109\/IROS58592.2024.10801753"},{"key":"ref6","article-title":"Slr: Learning quadruped locomotion without privileged information","author":"Chen","year":"2024"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2022.XVIII.022","article-title":"Rapid locomotion via reinforcement learning","author":"Margolis","year":"2022"},{"key":"ref8","article-title":"Hybrid internal model: Learning agile legged locomotion with simulated robot response","author":"Long","year":"2024"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2024.3457379","article-title":"Cts: Concurrent teacher-student reinforcement learning for legged locomotion","author":"Wang","year":"2024"},{"key":"ref10","doi-asserted-by":"crossref","volume-title":"Learning Bipedal Walking on a Quadruped Robot via Adversarial Motion Priors","author":"Peng","DOI":"10.1007\/978-3-031-72062-8_11"},{"key":"ref11","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"conference on Robot Learning (CoRL)","author":"Margolis"},{"key":"ref12","first-page":"112103","article-title":"DynaSTI: Dynamics modeling with sequential temporal information for reinforcement learning in Atari","volume":"299","author":"Kim"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2020.XVI.031","article-title":"Learning memory-based control for human-scale bipedal locomotion","author":"Siekmann","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3290509"},{"key":"ref15","doi-asserted-by":"crossref","volume-title":"Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control","author":"Li","DOI":"10.1177\/02783649241285161"},{"key":"ref16","article-title":"On covariate shift of latent confounders in imitation and reinforcement learning","author":"Tennenholtz","year":"2021"},{"issue":"23","key":"ref17","article-title":"Evaluating domain randomization in deep reinforcement learning locomotion tasks","volume-title":"Mathematics","volume":"11","author":"Ajani","year":"2023"},{"key":"ref18","article-title":"How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?","author":"Vuong","year":"2019"},{"key":"ref19","article-title":"Challenges of real-world reinforcement learning","author":"Dulac-Arnold"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA48891.2023.10161144","article-title":"Dreamwaq: Learning robust quadrupedal locomotion with implicit terrain imagination via deep reinforcement learning","author":"Nahrendra","year":"2023"},{"key":"ref21","article-title":"Data efficient reinforcement learning for legged robots","author":"Yang","year":"2019"},{"key":"ref22","article-title":"Dreamerpro: Reconstruction-free model-based reinforcement learning with prototypical representations","author":"Deng","year":"2021"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1016\/j.robot.2023.104432","article-title":"Dropo: Sim-to-real transfer with offline domain randomization","author":"Tiboni","year":"2023"},{"key":"ref24","article-title":"Reinforcement learning with prototypical representations","volume-title":"International Conference on Machine Learning","author":"Yarats"},{"key":"ref25","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"Caron","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref27","article-title":"Representation learning with contrastive predictive coding","author":"Van den Oord","year":"2019"},{"key":"ref28","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"ref29","article-title":"Curl: Contrastive unsupervised representations for reinforcement learning","author":"Srinivas","year":"2020"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00381","article-title":"Be your own teacher: Improve the performance of convolutional neural networks via self distillation","author":"Zhang","year":"2019"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref32","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247281.pdf?arnumber=11247281","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:15:55Z","timestamp":1765520155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247281\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247281","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}