{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T01:09:49Z","timestamp":1792717789019,"version":"4.5.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s11432-024-4396-3","type":"journal-article","created":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T23:24:35Z","timestamp":1745969075000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Causal action empowerment for efficient reinforcement learning in embodied agents"],"prefix":"10.1007","volume":"68","author":[{"given":"Hongye","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Huo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,24]]},"reference":[{"key":"4396_CR1","doi-asserted-by":"publisher","first-page":"5721","DOI":"10.1038\/s41467-021-25874-z","volume":"12","author":"A Gupta","year":"2021","unstructured":"Gupta A, Savarese S, Ganguli S, et al. Embodied intelligence via learning and evolution. Nat Commun, 2021, 12: 5721","journal-title":"Nat Commun"},{"key":"4396_CR2","first-page":"12123","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J Li","year":"2020","unstructured":"Li J, Wang X, Tang S, et al. Unsupervised reinforcement learning of transferable meta-skills for embodied navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020. 12123\u201312132"},{"key":"4396_CR3","first-page":"335","volume-title":"Proceedings of the 26th European Conference on Artificial Intelligence","author":"H Cao","year":"2023","unstructured":"Cao H, Yang S, Huo J, et al. Enhancing OOD generalization in offline reinforcement learning with energy-based policy optimization. In: Proceedings of the 26th European Conference on Artificial Intelligence, 2023. 335\u2013342"},{"key":"4396_CR4","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Y Ze","year":"2024","unstructured":"Ze Y, Liu Y, Shi R, et al. H-InDex: visual reinforcement learning with hand-informed representations for dexterous manipulation. In: Proceedings of Advances in Neural Information Processing Systems, 2024"},{"key":"4396_CR5","first-page":"9339","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"M Savva","year":"2019","unstructured":"Savva M, Kadian A, Maksymets O, et al. Habitat: a platform for embodied AI research. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019. 9339\u20139347"},{"key":"4396_CR6","first-page":"1395","volume":"22","author":"O Kroemer","year":"2021","unstructured":"Kroemer O, Niekum S, Konidaris G. A review of robot learning for manipulation: challenges, representations, and algorithms. J Machine Learn Res, 2021, 22: 1395\u20131476","journal-title":"J Machine Learn Res"},{"key":"4396_CR7","unstructured":"Zeng Y, Cai R, Sun F, et al. A survey on causal reinforcement learning. 2023. ArXiv:2302.05209"},{"key":"4396_CR8","unstructured":"Gupta T, Gong W, Ma C, et al. The essential role of causality in foundation world models for embodied AI. 2024. ArXiv:2402.06665"},{"key":"4396_CR9","unstructured":"Cao H, Feng F, Fang M, et al. Towards empowerment gain through causal structure learning in model-based RL. 2025. ArXiv:2502.10077"},{"key":"4396_CR10","unstructured":"Cao H, Feng F, Yang T, et al. Causal information prioritization for efficient reinforcement learning. 2025. ArXiv:2502.10097"},{"key":"4396_CR11","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"F Feng","year":"2023","unstructured":"Feng F, Magliacane S. Learning dynamic attribute-factored world models for efficient multi-object reinforcement learning. In: Proceedings of Advances in Neural Information Processing Systems, 2023"},{"key":"4396_CR12","first-page":"23151","volume-title":"Proceedings of International Conference on Machine Learning","author":"Z Wang","year":"2022","unstructured":"Wang Z, Xiao X, Xu Z, et al. Causal dynamics learning for task-independent state abstraction. In: Proceedings of International Conference on Machine Learning, 2022. 23151\u201323180"},{"key":"4396_CR13","first-page":"26532","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"W Ding","year":"2022","unstructured":"Ding W, Lin H, Li B, et al. Generalizing goal-conditioned reinforcement learning with variational causal reasoning. In: Proceedings of Advances in Neural Information Processing Systems, 2022. 26532\u201326548"},{"key":"4396_CR14","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1037\/0003-066X.33.5.437","volume":"33","author":"J Wolpe","year":"1978","unstructured":"Wolpe J. Cognition and causation in human behavior and its therapy. Am Psychologist, 1978, 33: 437\u2013446","journal-title":"Am Psychologist"},{"key":"4396_CR15","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"T Ji","year":"2024","unstructured":"Ji T, Liang Y, Zeng Y, et al. ACE: off-policy actor-critic with causality-aware entropy regularization. In: Proceedings of the 41st International Conference on Machine Learning, 2024"},{"key":"4396_CR16","unstructured":"Deng Z, Jiang J, Long G, et al. Causal reinforcement learning: a survey. 2023. ArXiv:2307.01452"},{"key":"4396_CR17","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems, Robot Learning workshop","author":"Z Wang","year":"2021","unstructured":"Wang Z, Xiao X, Zhu Y, et al. Task-independent causal state abstraction. In: Proceedings of the 35th International Conference on Neural Information Processing Systems, Robot Learning workshop, 2021"},{"key":"4396_CR18","volume-title":"Proceedings of International Conference on Learning Representations","author":"B Huang","year":"2022","unstructured":"Huang B, Feng F, Lu C, et al. AdaRL: what, where, and how to adapt in transfer reinforcement learning. In: Proceedings of International Conference on Learning Representations, 2022"},{"key":"4396_CR19","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s11431-023-2502-9","volume":"67","author":"K X Zhang","year":"2024","unstructured":"Zhang K X, Sun Q Y, Zhao C Q, et al. Causal reasoning in typical computer vision tasks. Sci China Tech Sci, 2024, 67: 105\u2013120","journal-title":"Sci China Tech Sci"},{"key":"4396_CR20","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"T Ji","year":"2024","unstructured":"Ji T, Luo Y, Sun F, et al. Seizing serendipity: exploiting the value of past success in off-policy actor-critic. In: Proceedings of the 41st International Conference on Machine Learning, 2024"},{"key":"4396_CR21","first-page":"1094","volume-title":"Proceedings of Conference on Robot Learning","author":"T Yu","year":"2020","unstructured":"Yu T, Quillen D, He Z, et al. Meta-World: a benchmark and evaluation for multi-task and meta reinforcement learning. In: Proceedings of Conference on Robot Learning, 2020. 1094\u20131100"},{"key":"4396_CR22","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"A Majumdar","year":"2024","unstructured":"Majumdar A, Yadav K, Arnaud S, et al. Where are we in the search for an artificial visual cortex for embodied intelligence? In: Proceedings of Advances in Neural Information Processing Systems, 2024"},{"key":"4396_CR23","volume-title":"Proceedings of Robotics: Science and Systems XIV","author":"A Rajeswaran","year":"2018","unstructured":"Rajeswaran A, Kumar V, Gupta A, et al. Learning complex dexterous manipulation with deep reinforcement learning and demonstrations. In: Proceedings of Robotics: Science and Systems XIV, 2018"},{"key":"4396_CR24","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"T Schmied","year":"2024","unstructured":"Schmied T, Hofmarcher M, Paischer F, et al. Learning to modulate pre-trained models in RL. In: Proceedings of Advances in Neural Information Processing Systems, 2024"},{"key":"4396_CR25","first-page":"5026","volume-title":"Proceedings of IEEE\/RSJ International Conference on Intelligent Robots and Systems","author":"E Todorov","year":"2012","unstructured":"Todorov E, Erez T, and Tassa Y. MuJoCo: a physics engine for model-based control. In: Proceedings of IEEE\/RSJ International Conference on Intelligent Robots and Systems, 2012. 5026\u20135033"},{"key":"4396_CR26","unstructured":"Tassa Y, Doron Y, Muldal A, et al. Deepmind control suite. 2018. ArXiv:1801.00690"},{"key":"4396_CR27","first-page":"639","volume-title":"Proceedings of Learning for Dynamics and Control Conference","author":"S Gurumurthy","year":"2023","unstructured":"Gurumurthy S, Kolter J Z, Manchester Z. Deep off-policy iterative learning control. In: Proceedings of Learning for Dynamics and Control Conference, 2023. 639\u2013652"},{"key":"4396_CR28","first-page":"27225","volume-title":"Proceedings of International Conference on Machine Learning","author":"S Park","year":"2023","unstructured":"Park S, Lee K, Lee Y, et al. Controllability-aware unsupervised skill discovery. In: Proceedings of International Conference on Machine Learning, 2023. 27225\u201327245"},{"key":"4396_CR29","volume-title":"Proceedings of the 35th Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"N R Ke","year":"2021","unstructured":"Ke N R, Didolkar A R, Mittal S, et al. Systematic evaluation of causal discovery in visual model based reinforcement learning. In: Proceedings of the 35th Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2021"},{"key":"4396_CR30","first-page":"9251","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"M Mutti","year":"2023","unstructured":"Mutti M, de Santi R, Rossi E, et al. Provably efficient causal model-based reinforcement learning for systematic generalization. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2023. 9251\u20139259"},{"key":"4396_CR31","first-page":"128","volume-title":"Proceedings of IEEE Congress on Evolutionary Computation","author":"A S Klyubin","year":"2005","unstructured":"Klyubin A S, Polani D, Nehaniv C L. Empowerment: a universal agent-centric measure of control. In: Proceedings of IEEE Congress on Evolutionary Computation, 2005. 128\u2013135"},{"key":"4396_CR32","unstructured":"Salge C, Glackin C, Polani D. Empowerment \u2014 an introduction. 2013. ArXiv:1310.1863"},{"key":"4396_CR33","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"S Mohamed","year":"2015","unstructured":"Mohamed S, Jimenez Rezende D. Variational information maximisation for intrinsically motivated reinforcement learning. In: Proceedings of Advances in Neural Information Processing Systems, 2015"},{"key":"4396_CR34","volume-title":"Proceedings of International Conference on Learning Representations","author":"H Bharadhwaj","year":"2022","unstructured":"Bharadhwaj H, Babaeizadeh M, Erhan D, et al. Information prioritization through empowerment in visual model-based RL. In: Proceedings of International Conference on Learning Representations, 2022"},{"key":"4396_CR35","unstructured":"Choi J, Sharma A, Lee H, et al. Variational empowerment as representation learning for goal-based reinforcement learning. 2021. ArXiv:2106.01404"},{"key":"4396_CR36","volume-title":"Proceedings of International Conference on Learning Representations","author":"B Eysenbach","year":"2018","unstructured":"Eysenbach B, Gupta A, Ibarz J, et al. Diversity is all you need: learning skills without a reward function. In: Proceedings of International Conference on Learning Representations, 2018"},{"key":"4396_CR37","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"F Leibfried","year":"2019","unstructured":"Leibfried F, Pascual-Diaz S, Grau-Moya J. A unified bellman optimality principle combining reward maximization and empowerment. In: Proceedings of Advances in Neural Information Processing Systems, 2019"},{"key":"4396_CR38","first-page":"22905","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"M Seitzer","year":"2021","unstructured":"Seitzer M, Sch\u00f6lkopf B, Martius G. Causal influence detection for improving efficiency in reinforcement learning. In: Proceedings of Advances in Neural Information Processing Systems, 2021. 22905\u201322918"},{"key":"4396_CR39","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161","volume-title":"Causality","author":"J Pearl","year":"2009","unstructured":"Pearl J. Causality. Cambridge: Cambridge University Press, 2009"},{"key":"4396_CR40","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1613\/jair.1000","volume":"19","author":"C Guestrin","year":"2003","unstructured":"Guestrin C, Koller D, Parr R, et al. Efficient solution algorithms for factored MDPs. J Artif Intell Res, 2003, 19: 399\u2013468","journal-title":"J Artif Intell Res"},{"key":"4396_CR41","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"C Guestrin","year":"2001","unstructured":"Guestrin C, Koller D, Parr R. Multiagent planning with factored MDPs. In: Proceedings of Advances in Neural Information Processing Systems, 2001"},{"key":"4396_CR42","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1754.001.0001","volume-title":"Causation, Prediction, and Search","author":"P Spirtes","year":"2001","unstructured":"Spirtes P, Glymour C, Scheines R. Causation, Prediction, and Search. Cambridge: MIT Press, 2001"},{"key":"4396_CR43","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1177\/1059712310392389","volume":"19","author":"T Jung","year":"2011","unstructured":"Jung T, Polani D, Stone P. Empowerment for continuous agent-environment systems. Adapt Behav, 2011, 19: 16\u201339","journal-title":"Adapt Behav"},{"key":"4396_CR44","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Y Liu","year":"2024","unstructured":"Liu Y, Huang B, Zhu Z, et al. Learning world models with identifiable factorization. In: Proceedings of Advances in Neural Information Processing Systems, 2024"},{"key":"4396_CR45","first-page":"1225","volume":"12","author":"S Shimizu","year":"2011","unstructured":"Shimizu S, Inazumi T, Sogawa Y, et al. DirectLiNGAM: a direct method for learning a linear non-Gaussian structural equation model. J Mach Learn Res, 2011, 12: 1225\u20131248","journal-title":"J Mach Learn Res"},{"key":"4396_CR46","first-page":"1861","volume-title":"Proceedings of International conference on machine learning","author":"T Haarnoja","year":"2018","unstructured":"Haarnoja T, Zhou A, Abbeel P, et al. Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Proceedings of International conference on machine learning, 2018. 1861\u20131870"},{"key":"4396_CR47","first-page":"29304","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"R Agarwal","year":"2021","unstructured":"Agarwal R, Schwarzer M, Castro P S, et al. Deep reinforcement learning at the edge of the statistical precipice. In: Proceedings of Advances in Neural Information Processing Systems, 2021. 29304\u201329320"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4396-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-024-4396-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4396-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T19:26:09Z","timestamp":1781897169000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-024-4396-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,24]]},"references-count":47,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["4396"],"URL":"https:\/\/doi.org\/10.1007\/s11432-024-4396-3","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,24]]},"assertion":[{"value":"1 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"150201"}}