{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T22:14:30Z","timestamp":1757456070683,"version":"3.32.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802420","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"380-387","source":"Crossref","is-referenced-by-count":1,"title":["Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planning"],"prefix":"10.1109","author":[{"given":"Yilue","family":"Qian","sequence":"first","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}]},{"given":"Peiyu","family":"Yu","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles (UCLA),Department of Statistics"}]},{"given":"Ying Nian","family":"Wu","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles (UCLA),Department of Statistics"}]},{"given":"Yao","family":"Su","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}]},{"given":"Lifeng","family":"Fan","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780195395761.013.0022"},{"article-title":"Llm 3: Large language model-based task and motion planning with motion failure reasoning","volume-title":"IEEE\/RAS International Conference on Intelligent Robots and Systems (IROS)","author":"Wang","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150855"},{"key":"ref5","article-title":"Action-conditional video prediction using deep networks in atari games","volume-title":"Advances in neural information processing systems","volume":"28","author":"Oh"},{"article-title":"Model-based reinforcement learning via latent-space collocation","volume-title":"International Conference on Machine Learning","author":"Rybkin","key":"ref6"},{"article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","year":"2018","author":"Ebert","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793736"},{"article-title":"Hallucinative topological memory for zero-shot visual planning","volume-title":"International Conference on Machine Learning","author":"Liu","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2023.3272513"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.003"},{"article-title":"Assessing generalization in deep reinforcement learning","year":"2018","author":"Packer","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.011"},{"article-title":"On disentangled representations learned from correlated data","volume-title":"International Conference on Machine Learning","author":"Tr\u00e4uble","key":"ref14"},{"key":"ref15","first-page":"1811","article-title":"Interventional robustness of deep latent variable models","author":"Suter","year":"2018"},{"article-title":"Discovering interpretable representations for both deep generative and discriminative models","volume-title":"International Conference on Machine Learning","author":"Adel","key":"ref16"},{"key":"ref17","first-page":"1462","article-title":"A causal view of compositional zero-shot recognition","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Atzmon"},{"article-title":"Darla: Improving zero-shot transfer in reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Higgins","key":"ref18"},{"article-title":"Weakly-supervised disentanglement without compromises","volume-title":"International Conference on Machine Learning","author":"Locatello","key":"ref19"},{"volume-title":"Learning How and Why: Causal Learning and Explanation from Physical, Interactive, and Communicative Environments","year":"2021","author":"Edmonds","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3501714.3501755"},{"issue":"1","key":"ref22","first-page":"327","article-title":"Neural-symbolic learning and reasoning: A survey and interpretation","volume":"342","author":"Garcez","year":"2022","journal-title":"Neuro-Symbolic Artificial Intelligence: The State of the Art"},{"article-title":"Diffskill: Skill abstraction from differentiable physics for deformable object manipulations with tools","year":"2022","author":"Lin","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635941"},{"article-title":"Is disentanglement all you need? comparing concept-based & disentanglement approaches","year":"2021","author":"Kazhdan","key":"ref25"},{"key":"ref26","article-title":"Are disentangled representations helpful for abstract visual reasoning?","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Van Steenkiste"},{"article-title":"Latent diffusion energy-based model for interpretable text modelling","volume-title":"International Conference on Machine Learning","author":"Yu","key":"ref27"},{"key":"ref28","article-title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets","volume-title":"Advances in neural information processing systems","volume":"29","author":"Chen"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00657"},{"article-title":"Early visual concept learning with unsupervised deep learning","year":"2016","author":"Higgins","key":"ref30"},{"article-title":"Visual concepts tokenization","year":"2022","author":"Yang","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01007"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01329"},{"article-title":"The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision","year":"2019","author":"Mao","key":"ref34"},{"article-title":"Egotaskqa: Understanding human tasks in egocentric videos","year":"2022","author":"Jia","key":"ref35"},{"article-title":"Clevrer: Collision events for video representation and reasoning","year":"2019","author":"Yi","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.13"},{"article-title":"AI2-THOR: An Interactive 3D Environment for Visual AI","year":"2017","author":"Kolve","key":"ref38"},{"article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","volume-title":"International Conference on learning representations","author":"Higgins","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"article-title":"Prioritized experience replay","year":"2015","author":"Schaul","key":"ref41"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802420.pdf?arnumber=10802420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:00:53Z","timestamp":1735196453000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802420","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}