{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:39:32Z","timestamp":1784133572399,"version":"3.55.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61825305"],"award-info":[{"award-number":["61825305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20518"],"award-info":[{"award-number":["U21A20518"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tnnls.2023.3296642","type":"journal-article","created":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T17:40:03Z","timestamp":1692121203000},"page":"16574-16588","source":"Crossref","is-referenced-by-count":12,"title":["Sample Efficient Deep Reinforcement Learning With Online State Abstraction and Causal Transformer Model Prediction"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4503-643X","authenticated-orcid":false,"given":"Yixing","family":"Lan","sequence":"first","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3238-745X","authenticated-orcid":false,"given":"Xin","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Fang","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0422-8235","authenticated-orcid":false,"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref4","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. ICML","author":"Haarnoja"},{"key":"ref5","first-page":"741","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Lee"},{"key":"ref6","article-title":"Model based reinforcement learning for Atari","volume-title":"Proc. ICLR","author":"Kaiser"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref9","first-page":"8766","article-title":"Unsupervised state representation learning in Atari","volume-title":"Proc. NeurIPS","author":"Anand"},{"key":"ref10","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. 9th Int. Conf. Learn. Represent., (ICLR)","author":"Yarats"},{"key":"ref11","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Laskin"},{"key":"ref12","article-title":"Learning invariant representations for reinforcement learning without reconstruction","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Zhang"},{"key":"ref13","first-page":"2170","article-title":"DeepMDP: Learning continuous latent space models for representation learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"97","author":"Gelada"},{"key":"ref14","article-title":"Return-based contrastive representation learning for reinforcement learning","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref15","article-title":"A theory of abstraction in reinforcement learning","author":"Abel","year":"2022","journal-title":"arXiv:2203.00397"},{"key":"ref16","article-title":"Model-augmented actor-critic: Backpropagating through paths","volume-title":"Proc. ICLR","author":"Clavera"},{"key":"ref17","first-page":"3686","article-title":"Deep reinforcement and InfoMax learning","volume-title":"Proc. NeurIPS","author":"Mazoure"},{"key":"ref18","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"Proc. ICLR","author":"Hafner"},{"key":"ref19","article-title":"DeepMind control suite","author":"Tassa","year":"2018","journal-title":"arXiv:1801.00690"},{"key":"ref20","first-page":"264","article-title":"Lipschitz continuity in model-based reinforcement learning","volume-title":"Proc. ICML","volume":"80","author":"Asadi"},{"key":"ref21","article-title":"A survey on model-based reinforcement learning","author":"Luo","year":"2022","journal-title":"arXiv:2206.09328"},{"key":"ref22","article-title":"Combating the compounding-error problem with a multi-step model","author":"Asadi","year":"2019","journal-title":"arXiv:1905.13320"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.strusafe.2008.06.020"},{"key":"ref24","first-page":"179","article-title":"Abstraction selection in model-based reinforcement learning","volume-title":"Proc. 32nd Int. Conf. Mach. Learn. (ICML)","volume":"37","author":"Jiang"},{"key":"ref25","article-title":"Transfer with model features in reinforcement learning","author":"Lehnert","year":"2018","journal-title":"arXiv:1807.01736"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10850"},{"key":"ref27","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chen"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2891792"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00376-4"},{"key":"ref31","article-title":"Mastering Atari with discrete world models","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Hafner"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3107375"},{"key":"ref33","article-title":"Learning state representations via retracing in reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref34","article-title":"Deep reinforcement learning with relational inductive biases","volume-title":"Proc. ICLR","author":"Zambaldi"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3220798"},{"key":"ref36","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume-title":"Proc. NeurIPS","author":"Janner"},{"key":"ref37","first-page":"27344","article-title":"Unsupervised object-based transition models for 3D partially observable environments","volume-title":"Proc. NeurIPS","author":"Creswell"},{"key":"ref38","first-page":"11307","article-title":"Generative video transformer: Can objects be the words?","volume-title":"Proc. ICML","volume":"139","author":"Wu"},{"key":"ref39","article-title":"TransDreamer: Reinforcement learning with transformer world models","author":"Chen","year":"2022","journal-title":"arXiv:2202.09481"},{"key":"ref40","article-title":"Transformers are sample efficient world models","author":"Micheli","year":"2022","journal-title":"arXiv:2209.00588"},{"key":"ref41","first-page":"162","article-title":"Metrics for finite Markov decision processes","volume-title":"Proc. UAI","author":"Ferns"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1137\/10080484X"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6564"},{"key":"ref44","article-title":"\u00df-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. ICLR","author":"Higgins"},{"key":"ref45","first-page":"3432","article-title":"Stochastic optimization for large-scale optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Genevay"},{"key":"ref46","first-page":"5767","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. NeurIPS","author":"Gulrajani"},{"key":"ref47","article-title":"Importance of using appropriate baselines for evaluation of data-efficiency in deep reinforcement learning for Atari","author":"Kielak","year":"2020","journal-title":"arXiv:2003.10181"},{"key":"ref48","first-page":"14322","article-title":"When to use parametric models in reinforcement learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"van Hasselt"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993308"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10737991\/10219179.pdf?arnumber=10219179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:27:44Z","timestamp":1732735664000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10219179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":50,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3296642","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}