{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T13:18:47Z","timestamp":1780579127701,"version":"3.54.1"},"reference-count":96,"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\/icra55743.2025.11128025","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"9516-9524","source":"Crossref","is-referenced-by-count":1,"title":["GHIL-Glue: Hierarchical Control with Filtered Subgoal Images"],"prefix":"10.1109","author":[{"given":"Kyle B.","family":"Hatch","sequence":"first","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashwin","family":"Balakrishna","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oier","family":"Mees","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suraj","family":"Nair","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seohong","family":"Park","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Blake","family":"Wulfe","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masha","family":"Itkina","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Eysenbach","sequence":"additional","affiliation":[{"name":"Princeton University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Kollar","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Burchfiel","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Robonet: Large-scale multi-robot learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Dasari","year":"2019"},{"key":"ref2","author":"O\u2019Neill","year":"2024","journal-title":"Open X-Embodiment: Robotic learning datasets and RT-X models"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref4","article-title":"Zero-shot robotic manipulation with pretrained image-editing diffusion models","author":"Black","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Learning universal policies via text-guided video generation","volume":"36","author":"Du","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3272516"},{"key":"ref7","article-title":"Video language planning","author":"Du","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Compositional foundation models for hierarchical planning","volume":"36","author":"Ajay","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"Can pre-trained text-to-image models generate visual goals for reinforcement learning?","volume":"36","author":"Gao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref11","article-title":"Bridgedata v2: A dataset for robot learning at scale","volume-title":"Conference on Robot Learning (CoRL)","author":"Walke"},{"key":"ref12","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning. PMLR","author":"Sohl-Dickstein","year":"2015"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref17","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Octo: An open-source generalist robot policy","volume-title":"Proceedings of Robotics: Science and Systems","author":"Model Team"},{"key":"ref19","article-title":"Scaling cross-embodied learning: One policy for manipulation, navigation, locomotion and aviation","volume-title":"Conference on Robot Learning","author":"Doshi","year":"2024"},{"key":"ref20","article-title":"Robotic control via embodied chain-of-thought reasoning","volume-title":"Conference on Robot Learning","author":"Zawalski","year":"2024"},{"key":"ref21","article-title":"The ingredients for robotic diffusion transformers","author":"Dasari","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Cacti: A framework for scalable multi-task multi-scene visual imitation learning","author":"Mandi","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.010"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.027"},{"key":"ref25","article-title":"Open-world object manipulation using pre-trained vision-language models","author":"Stone","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Learning with language-guided state abstractions","author":"Peng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"International Conference on Machine Learning. PMLR","author":"Huang","year":"2022"},{"key":"ref28","article-title":"Inner monologue: Embodied reasoning through planning with language models","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"287","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conference on robot learning. PMLR","author":"Brohan","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref31","article-title":"Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Autonomous improvement of instruction following skills via foundation models","volume-title":"Conference on Robot Learning","author":"Zhou","year":"2024"},{"key":"ref33","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International conference on machine learning. PMLR","author":"Fujimoto","year":"2019"},{"key":"ref34","first-page":"3682","article-title":"Emaq: Expected-max q-learning operator for simple yet effective offline and online rl","volume-title":"International Conference on Machine Learning. PMLR","author":"Ghasemipour","year":"2021"},{"key":"ref35","article-title":"Offline reinforcement learning via high-fidelity generative behavior modeling","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Idql: Implicit q-learning as an actor-critic method with diffusion policies","author":"Hansen-Estruch","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Steering your generalists: Improving robotic foundation models via value guidance","volume-title":"Conference on Robot Learning (CoRL)","author":"Nakamoto","year":"2024"},{"key":"ref38","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Let\u2019s verify step by step","author":"Lightman","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"V-star: Training verifiers for self-taught reasoners","author":"Hosseini","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.031"},{"key":"ref42","article-title":"Grounded decoding: Guiding text generation with grounded models for robot control","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.089"},{"key":"ref44","article-title":"Robots that ask for help: Uncertainty alignment for large language model planners","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Policy adaptation via language optimization: Decomposing tasks for few-shot imitation","volume-title":"Conference on Robot Learning","author":"Myers","year":"2024"},{"key":"ref46","article-title":"Learning language-conditioned robot behavior from offline data and crowd-sourced annotation","volume-title":"Conference on Robot Learning (CoRL)","author":"Nair"},{"key":"ref47","first-page":"1094","article-title":"Learning to achieve goals","volume":"2","author":"Kaelbling","year":"1993","journal-title":"IJCAI"},{"key":"ref48","first-page":"1312","article-title":"Universal value function approximators","volume-title":"International conference on machine learning. PMLR","author":"Schaul","year":"2015"},{"key":"ref49","article-title":"Hind-sight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-101119-071628"},{"key":"ref51","first-page":"13 139","article-title":"Language-conditioned imitation learning for robot manipulation tasks","volume":"33","author":"Stepputtis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196123"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160396"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.047"},{"key":"ref55","article-title":"Lelan: Learning a language-conditioned navigation policy from in-the-wild video","volume-title":"Conference on Robot Learning","author":"Hirose","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196935"},{"key":"ref57","article-title":"Hiql: Offline goal-conditioned rl with latent states as actions","volume":"36","author":"Park","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref60","first-page":"967","article-title":"Learning to generate sub-goals for action sequences","author":"Schmidhuber","year":"1991","journal-title":"Artificial neural networks"},{"key":"ref61","article-title":"Feudal reinforcement learning","volume":"5","author":"Dayan","year":"1992","journal-title":"Advances in neural information processing systems"},{"key":"ref62","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume":"29","author":"Kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref63","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"International conference on machine learning. PMLR","author":"Vezhnevets","year":"2017"},{"key":"ref64","article-title":"Learning multi-level hierarchies with hindsight","author":"Levy","year":"2017","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Data-efficient hierarchical reinforcement learning","volume":"31","author":"Nachum","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref66","article-title":"Near-optimal representation learning for hierarchical reinforcement learning","author":"Nachum","year":"2018","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","author":"Gupta","year":"2019","journal-title":"arXiv preprint"},{"key":"ref68","article-title":"Opal: Offline primitive discovery for accelerating offline reinforcement learning","author":"Ajay","year":"2020","journal-title":"arXiv preprint"},{"key":"ref69","first-page":"1113","article-title":"Learning latent plans from play","volume-title":"Conference on Robot Learning (CoRL). PMLR","author":"Lynch","year":"2020"},{"key":"ref70","first-page":"1838","article-title":"Latent plans for task-agnostic offline reinforcement learning","volume-title":"Conference on Robot Learning. PMLR","author":"Rosete-Beas","year":"2023"},{"key":"ref71","first-page":"21 579","article-title":"Generating adjacency-constrained subgoals in hierarchical reinforcement learning","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref72","first-page":"188","article-title":"Accelerating reinforcement learning with learned skill priors","volume-title":"Conference on robot learning. PMLR","author":"Pertsch","year":"2021"},{"key":"ref73","first-page":"1430","article-title":"Goal-conditioned reinforcement learning with imagined subgoals","volume-title":"International Conference on Machine Learning. PMLR","author":"Chane-Sane","year":"2021"},{"key":"ref74","article-title":"Semi-parametric topological memory for navigation","author":"Savinov","year":"2018","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","volume":"32","author":"Eysenbach","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref76","article-title":"Hierarchical foresight: Self-supervised learning of long-horizon tasks via visual subgoal generation","author":"Nair","year":"2019","journal-title":"arXiv preprint"},{"key":"ref77","article-title":"Planning with goal-conditioned policies","volume":"32","author":"Nasiriany","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref78","article-title":"Mapping state space using landmarks for universal goal reaching","volume":"32","author":"Huang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref79","first-page":"26963","article-title":"Successor feature landmarks for long-horizon goal-conditioned reinforcement learning","volume":"34","author":"Hoang","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref80","first-page":"28336","article-title":"Landmark-guided subgoal generation in hierarchical reinforcement learning","volume":"34","author":"Kim","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref81","first-page":"12611","article-title":"World model as a graph: Learning latent landmarks for planning","volume-title":"International conference on machine learning. PMLR","author":"Zhang","year":"2021"},{"key":"ref82","article-title":"Rapid exploration for open-world navigation with latent goal models","author":"Shah","year":"2021","journal-title":"arXiv preprint"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981999"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3190100"},{"key":"ref85","article-title":"Imitating graph-based planning with goal-conditioned policies","author":"Kim","year":"2023","journal-title":"arXiv preprint"},{"key":"ref86","first-page":"106","article-title":"Generalization with lossy affordances: Leveraging broad offline data for learning visuomotor tasks","volume-title":"Conference on Robot Learning. PMLR","author":"Fang","year":"2023"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref89","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref90","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref91","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in neural information processing systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref94","article-title":"Stabilizing contrastive rl: Techniques for offline goal reaching","author":"Zheng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref95","article-title":"The","volume-title":"IEEE international conference on computer vision (ICCV)","author":"Goyal","year":"2017"},{"key":"ref96","article-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"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\/11128025.pdf?arnumber=11128025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:03:24Z","timestamp":1756879404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":96,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128025","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}