{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:14:16Z","timestamp":1766139256771,"version":"3.44.0"},"reference-count":75,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128478","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"14441-14448","source":"Crossref","is-referenced-by-count":2,"title":["Learning Multi-Agent Loco-Manipulation for Long-Horizon Quadrupedal Pushing"],"prefix":"10.1109","author":[{"given":"Yuming","family":"Feng","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Chuye","family":"Hong","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Yaru","family":"Niu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Shiqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Yuxiang","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Ding","family":"Zhao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.ade2256"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00144"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104134"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610200"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794273"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981779"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801980"},{"key":"ref10","article-title":"Umi on legs: Making manipulation policies mobile with manipulation-centric whole-body controllers","author":"Ha","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"138","article-title":"Deep whole-body control: learning a unified policy for manipulation and locomotion","volume-title":"Conference on Robot Learning. PMLR","author":"Fu"},{"key":"ref12","article-title":"Visual whole-body control for legged loco-manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561926"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160325"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids58906.2024.10769896"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161470"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160507"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160523"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965906"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341498"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3335777"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341700"},{"key":"ref23","article-title":"Multi-agent manipulation via locomotion using hierarchical sim2real","author":"Nachum","year":"2019","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Solving multi-entity robotic problems using permutation invariant neural networks","author":"An","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801682"},{"volume-title":"Rapidly-exploring random trees: A new tool for path planning","year":"1998","author":"LaValle","key":"ref26"},{"key":"ref27","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10146-0"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139995"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3286171"},{"key":"ref31","article-title":"Bayrntune: Adaptive bayesian domain randomization via strategic fine-tuning","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Learning to open and traverse doors with a legged manipulator","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Wococo: Learning whole-body humanoid control with sequential contacts","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611307"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610125"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461263"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3072021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2400731"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.063"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3060379"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MRS50823.2021.9620665"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.1995.525940"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160914"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1115\/1.4052917"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3319896"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.050"},{"key":"ref47","article-title":"Distributed reinforcement learning for cooperative multi-robot object manipulation","author":"Ding","year":"2020","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Dair: Disentangled attention intrinsic regularization for safe and efficient bimanual manipulation","author":"Zhang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160739"},{"article-title":"Learning to coordinate manipulation skills via skill behavior diversification","volume-title":"International conference on learning representations","author":"Lee","key":"ref50"},{"key":"ref51","article-title":"Dynamic handover: Throw and catch with bimanual hands","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","first-page":"5150","article-title":"Towards human-level bimanual dexterous manipulation with reinforcement learning","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49439.2021.9551481"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611040"},{"key":"ref55","article-title":"Learning decentralized multi-biped control for payload transport","author":"Pandit","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Data-efficient hierarchical reinforcement learning","volume":"31","author":"Nachum","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref57","article-title":"Near-optimal representation learning for hierarchical reinforcement learning","author":"Nachum","year":"2018","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Learning multi-level hierarchies with hindsight","author":"Levy","year":"2017","journal-title":"arXiv preprint"},{"key":"ref59","first-page":"3540","article-title":"Feudal networks for hierarchical rein-forcement learning","volume-title":"International conference on machine learning","author":"Vezhnevets"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812140"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196619"},{"key":"ref62","article-title":"Hierarchical deep multiagent reinforcement learning with temporal abstraction","author":"Tang","year":"2018","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Feudal multi-agent hierarchies for cooperative reinforcement learning","author":"Ahilan","year":"2019","journal-title":"arXiv preprint"},{"key":"ref64","first-page":"816","article-title":"Feudal multi -agent deep reinforcement learning for traffic signal control","volume-title":"Proceedings of the 19th international conference on autonomous agents and multiagent systems (AAMAS)","author":"Ma"},{"key":"ref65","first-page":"6860","article-title":"Coach-player multi-agent reinforcement learning for dynamic team composition","volume-title":"International Conference on Machine Learning","author":"Liu"},{"article-title":"Visual-locomotion: Learning to walk on complex terrains with vision","volume-title":"5th Annual Conference on Robot Learning","author":"Yu","key":"ref66"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3172469"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636757"},{"key":"ref69","article-title":"Humanplus: Humanoid shadowing and imitation from humans","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","first-page":"773","article-title":"Fast and efficient locomotion via learned gait transitions","volume-title":"Conference on robot learning","author":"Yang"},{"key":"ref71","first-page":"883","article-title":"Learning a contact-adaptive controller for robust, efficient legged locomotion","volume-title":"Conference on robot learning","author":"Da"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.5040\/9781635577068-0320"},{"key":"ref73","first-page":"22","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"Conference on Robot Learning","author":"Margolis"},{"key":"ref74","first-page":"24 611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref75","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128478.pdf?arnumber=11128478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:13:26Z","timestamp":1756880006000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128478\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128478","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}