{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T11:46:30Z","timestamp":1784029590995,"version":"3.55.0"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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":["Front. Comput. Sci."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s11704-024-3194-1","type":"journal-article","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T07:19:00Z","timestamp":1732259940000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Clustered Reinforcement Learning"],"prefix":"10.1007","volume":"19","author":[{"given":"Xiao","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shen-Yi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao-Heng","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wu-Jun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"3194_CR1","volume-title":"Reinforcement Learning: an Introduction","author":"R S Sutton","year":"1998","unstructured":"Sutton R S, Barto A G. Reinforcement Learning: an Introduction. Cambridge: MIT Press, 1998"},{"issue":"7540","key":"3194_CR2","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu A A, Veness J, Bellemare M G, Graves A, Riedmiller M, Fidjeland A K, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D. Human-level control through deep reinforcement learning. Nature, 2015, 518(7540): 529\u2013533","journal-title":"Nature"},{"issue":"7587","key":"3194_CR3","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison C J, Guez A, Sifre L, Van Den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M, Dieleman S, Grewe D, Nham J, Kalchbrenner N, Sutskever I, Lillicrap T P, Leach M, Kavukcuoglu K, Graepel T, Hassabis D. Mastering the game of go with deep neural networks and tree search. Nature, 2016, 529(7587): 484\u2013489","journal-title":"Nature"},{"key":"3194_CR4","first-page":"2140","volume-title":"Proceedings of the 31st AAAI Conference on Artificial Intelligence","author":"G Lample","year":"2017","unstructured":"Lample G, Chaplot D S. Playing FPS games with deep reinforcement learning. In: Proceedings of the 31st AAAI Conference on Artificial Intelligence. 2017, 2140\u20132146"},{"key":"3194_CR5","first-page":"48","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"A P Badia","year":"2020","unstructured":"Badia A P, Piot B, Kapturowski S, Sprechmann P, Vitvitskyi A, Guo D, Blundell C. Agent57: Outperforming the Atari human benchmark. In: Proceedings of the 37th International Conference on Machine Learning. 2020, 48"},{"issue":"12","key":"3194_CR6","doi-asserted-by":"publisher","first-page":"5163","DOI":"10.1007\/s10994-023-06365-2","volume":"112","author":"X Ma","year":"2023","unstructured":"Ma X, Li W J. State-based episodic memory for multi-agent reinforcement learning. Machine Learning, 2023, 112(12): 5163\u20135190","journal-title":"Machine Learning"},{"issue":"2","key":"3194_CR7","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1007\/s10462-021-09997-9","volume":"55","author":"B Singh","year":"2022","unstructured":"Singh B, Kumar R, Singh V P. Reinforcement learning in robotic applications: a comprehensive survey. Artificial Intelligence Review, 2022, 55(2): 945\u2013990","journal-title":"Artificial Intelligence Review"},{"issue":"6","key":"3194_CR8","doi-asserted-by":"publisher","first-page":"2346","DOI":"10.1109\/TCYB.2019.2890974","volume":"50","author":"Y Wen","year":"2020","unstructured":"Wen Y, Si J, Brandt A, Gao X, Huang H H. Online reinforcement learning control for the personalization of a robotic knee prosthesis. IEEE Transactions on Cybernetics, 2020, 50(6): 2346\u20132356","journal-title":"IEEE Transactions on Cybernetics"},{"key":"3194_CR9","volume-title":"Proceedings of the 4th International Conference on Learning Representations","author":"T P Lillicrap","year":"2016","unstructured":"Lillicrap T P, Hunt J J, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D. Continuous control with deep reinforcement learning. In: Proceedings of the 4th International Conference on Learning Representations. 2016"},{"key":"3194_CR10","first-page":"1329","volume-title":"Proceedings of the 33rd International Conference on Machine Learning","author":"Y Duan","year":"2016","unstructured":"Duan Y, Chen X, Houthooft R, Schulman J, Abbeel P. Benchmarking deep reinforcement learning for continuous control. In: Proceedings of the 33rd International Conference on Machine Learning. 2016, 1329\u20131338"},{"issue":"3","key":"3194_CR11","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1109\/TCYB.2015.2412554","volume":"46","author":"H Modares","year":"2016","unstructured":"Modares H, Ranatunga I, Lewis F L, Popa D O. Optimized assistive human-robot interaction using reinforcement learning. IEEE Transactions on Cybernetics, 2016, 46(3): 655\u2013667","journal-title":"IEEE Transactions on Cybernetics"},{"key":"3194_CR12","volume-title":"Deep reinforcement learning for robotic manipulation-the state of the art","author":"S Amarjyoti","year":"2017","unstructured":"Amarjyoti S. Deep reinforcement learning for robotic manipulation-the state of the art. 2017, arXiv preprint arXiv: 1701.08878"},{"key":"3194_CR13","first-page":"538","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","author":"Y Xu","year":"2022","unstructured":"Xu Y, Fang M, Chen L, Du Y, Zhou J, Zhang C. Perceiving the world: Question-guided reinforcement learning for text-based games. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. 2022, 538\u2013560"},{"key":"3194_CR14","first-page":"1267","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","author":"D Ghalandari","year":"2022","unstructured":"Ghalandari D, Hokamp C, Ifrim G. Efficient unsupervised sentence compression by fine-tuning transformers with reinforcement learning. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. 2022, 1267\u20131280"},{"issue":"4","key":"3194_CR15","doi-asserted-by":"publisher","first-page":"154328","DOI":"10.1007\/s11704-020-9322-7","volume":"15","author":"H Li","year":"2021","unstructured":"Li H, Hu Y, Cao Y, Zhou G, Luo P. Rich-text document styling restoration via reinforcement learning. Frontiers of Computer Science, 2021, 15(4): 154328","journal-title":"Frontiers of Computer Science"},{"issue":"5","key":"3194_CR16","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1007\/s11704-013-2291-3","volume":"7","author":"K L A Yau","year":"2013","unstructured":"Yau K L A, Kwong K H, Shen C. Reinforcement learning models for scheduling in wireless networks. Frontiers of Computer Science, 2013, 7(5): 754\u2013766","journal-title":"Frontiers of Computer Science"},{"issue":"5","key":"3194_CR17","doi-asserted-by":"publisher","first-page":"155105","DOI":"10.1007\/s11704-020-9273-z","volume":"15","author":"Y Qin","year":"2021","unstructured":"Qin Y, Wang H, Yi S, Li X, Zhai L. A multi-objective reinforcement learning algorithm for deadline constrained scientific workflow scheduling in clouds. Frontiers of Computer Science, 2021, 15(5): 155105","journal-title":"Frontiers of Computer Science"},{"key":"3194_CR18","doi-asserted-by":"publisher","first-page":"108894","DOI":"10.1016\/j.asoc.2022.108894","volume":"123","author":"Y C Lin","year":"2022","unstructured":"Lin Y C, Chen C T, Sang C Y, Huang S H. Multiagent-based deep reinforcement learning for risk-shifting portfolio management. Applied Soft Computing, 2022, 123: 108894","journal-title":"Applied Soft Computing"},{"issue":"1","key":"3194_CR19","first-page":"236","volume":"34","author":"Y Zhang","year":"2022","unstructured":"Zhang Y, Zhao P, Wu Q, Li B, Huang J, Tan M. Cost-sensitive portfolio selection via deep reinforcement learning. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(1): 236\u2013248","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"3194_CR20","first-page":"4028","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing","author":"X Li","year":"2022","unstructured":"Li X, Cui C, Cao D, Du J, Zhang C. Hypergraph-based reinforcement learning for stock portfolio selection. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. 2022, 4028\u20134032"},{"key":"3194_CR21","first-page":"641","volume-title":"Proceedings of the 29th International Joint Conference on Artificial Intelligence","author":"K Xu","year":"2020","unstructured":"Xu K, Zhang Y, Ye D, Zhao P, Tan M. Relation-aware transformer for portfolio policy learning. In: Proceedings of the 29th International Joint Conference on Artificial Intelligence. 2020, 641"},{"key":"3194_CR22","first-page":"643","volume-title":"Proceedings of the 35th AAAI Conference on Artificial Intelligence","author":"Z Wang","year":"2021","unstructured":"Wang Z, Huang B, Tu S, Zhang K, Xu L. DeepTrader: A deep reinforcement learning approach for risk-return balanced portfolio management with market conditions embedding. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence. 2021, 643\u2013650"},{"key":"3194_CR23","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"L Ouyang","year":"2022","unstructured":"Ouyang L, Wu J, Jiang X, Almeida D, Wainwright C L, Mishkin P, Zhang C, Agarwal S, Slama K, Ray A, Schulman J, Hilton J, Kelton F, Miller L, Simens M, Askell A, Welinder P, Christiano P F, Leike J, Lowe R. Training language models to follow instructions with human feedback. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022"},{"key":"3194_CR24","first-page":"2753","volume-title":"Proceedings of the 31th International Conference on Neural Information Processing Systems","author":"H R Tang","year":"2017","unstructured":"Tang H R, Houthooft R, Foote D, Stooke A, Chen X, Duan Y, Schulman J, De Turck F, Abbeel P. #exploration: A study of count-based exploration for deep reinforcement learning. In: Proceedings of the 31th International Conference on Neural Information Processing Systems. 2017, 2753\u20132762"},{"issue":"6","key":"3194_CR25","doi-asserted-by":"publisher","first-page":"156336","DOI":"10.1007\/s11704-020-0241-4","volume":"15","author":"H Qian","year":"2021","unstructured":"Qian H, Yu Y. Derivative-free reinforcement learning: a review. Frontiers of Computer Science, 2021, 15(6): 156336","journal-title":"Frontiers of Computer Science"},{"key":"3194_CR26","first-page":"2249","volume-title":"Proceedings of the 24th International Conference on Neural Information Processing Systems","author":"O Chapelle","year":"2011","unstructured":"Chapelle O, Li L. An empirical evaluation of Thompson sampling. In: Proceedings of the 24th International Conference on Neural Information Processing Systems. 2011, 2249\u20132257"},{"key":"3194_CR27","first-page":"1928","volume-title":"Proceedings of the 33rd International Conference on Machine Learning","author":"V Mnih","year":"2016","unstructured":"Mnih V, Badia A P, Mirza M, Graves A, Harley T, Lillicrap T P, Silver D, Kavukcuoglu K. Asynchronous methods for deep reinforcement learning. In: Proceedings of the 33rd International Conference on Machine Learning. 2016, 1928\u20131937"},{"key":"3194_CR28","volume-title":"Proceedings of the 6th International Conference on Learning Representations","author":"M Fortunato","year":"2018","unstructured":"Fortunato M, Azar M G, Piot B, Menick J, Hessel M, Osband I, Graves A, Mnih V, Munos R, Hassabis D, Pietquin O, Blundell C, Legg S. Noisy networks for exploration. In: Proceedings of the 6th International Conference on Learning Representations. 2018"},{"key":"3194_CR29","volume-title":"Proceedings of the 6th International Conference on Learning Representations","author":"M Plappert","year":"2018","unstructured":"Plappert M, Houthooft R, Dhariwal P, Sidor S, Chen R Y, Chen X, Asfour T, Abbeel P, Andrychowicz M. Parameter space noise for exploration. In: Proceedings of the 6th International Conference on Learning Representations. 2018"},{"key":"3194_CR30","first-page":"4033","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems","author":"I Osband","year":"2016","unstructured":"Osband I, Blundell C, Pritzel A, Van Roy B. Deep exploration via bootstrapped DQN. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. 2016, 4033\u20134041"},{"issue":"124","key":"3194_CR31","first-page":"1","volume":"20","author":"I Osband","year":"2019","unstructured":"Osband I, Van Roy B, Russo D J, Wen Z. Deep exploration via randomized value functions. Journal of Machine Learning Research, 2019, 20(124): 1\u201362","journal-title":"Journal of Machine Learning Research"},{"issue":"2\u20133","key":"3194_CR32","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1023\/A:1017984413808","volume":"49","author":"M Kearns","year":"2002","unstructured":"Kearns M, Singh S. Near-optimal reinforcement learning in polynomial time. Machine Learning, 2002, 49(2\u20133): 209\u2013232","journal-title":"Machine Learning"},{"key":"3194_CR33","first-page":"213","volume":"3","author":"R I Brafman","year":"2003","unstructured":"Brafman R I, Tennenholtz M. R-MAX - a general polynomial time algorithm for near-optimal reinforcement learning. Journal of Machine Learning Research, 2003, 3: 213\u2013231","journal-title":"Journal of Machine Learning Research"},{"key":"3194_CR34","first-page":"1479","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems","author":"M G Bellemare","year":"2016","unstructured":"Bellemare M G, Srinivasan S, Ostrovski G, Schaul T, Saxton D, Munos R. Unifying count-based exploration and intrinsic motivation. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. 2016, 1479\u20131487"},{"key":"3194_CR35","first-page":"2721","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"G Ostrovski","year":"2017","unstructured":"Ostrovski G, Bellemare M G, Van Den Oord A, Munos R. Count-based exploration with neural density models. In: Proceedings of the 34th International Conference on Machine Learning. 2017, 2721\u20132730"},{"key":"3194_CR36","first-page":"1117","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems","author":"R Houthooft","year":"2016","unstructured":"Houthooft R, Chen X, Duan Y, Schulman J, De Turck F, Abbeel P. VIME: variational information maximizing exploration. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. 2016, 1117\u20131125"},{"key":"3194_CR37","volume-title":"Incentivizing exploration in reinforcement learning with deep predictive models","author":"B C Stadie","year":"2015","unstructured":"Stadie B C, Levine S, Abbeel P. Incentivizing exploration in reinforcement learning with deep predictive models. 2015, arXiv preprint arXiv: 1507.00814"},{"key":"3194_CR38","first-page":"2778","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"D Pathak","year":"2017","unstructured":"Pathak D, Agrawal P, Efros A A, Darrell T. Curiosity-driven exploration by self-supervised prediction. In: Proceedings of the 34th International Conference on Machine Learning. 2017, 2778\u20132787"},{"key":"3194_CR39","first-page":"128","volume-title":"Proceedings of the 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 the IEEE Congress on Evolutionary Computation. 2005, 128\u2013135"},{"key":"3194_CR40","first-page":"2577","volume-title":"Proceedings of the 31th International Conference on Neural Information Processing Systems","author":"J Fu","year":"2017","unstructured":"Fu J, Co-Reyes J D, Levine S. EX2: exploration with exemplar models for deep reinforcement learning. In: Proceedings of the 31th International Conference on Neural Information Processing Systems. 2017, 2577\u20132587"},{"key":"3194_CR41","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"Y Burda","year":"2019","unstructured":"Burda Y, Edwards H, Storkey A J, Klimov O. Exploration by random network distillation. In: Proceedings of the 7th International Conference on Learning Representations. 2019"},{"key":"3194_CR42","first-page":"25217","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"T Zhang","year":"2021","unstructured":"Zhang T, Xu H, Wang X, Wu Y, Keutzer K, Gonzalez J E, Tian Y. NovelD: A simple yet effective exploration criterion. In: Proceedings of the 35th International Conference on Neural Information Processing Systems. 2021, 25217\u201325230"},{"key":"3194_CR43","first-page":"49","volume-title":"Proceedings of the 19th International Conference on Neural Information Processing Systems","author":"P Auer","year":"2006","unstructured":"Auer P, Ortner R. Logarithmic online regret bounds for undiscounted reinforcement learning. In: Proceedings of the 19th International Conference on Neural Information Processing Systems. 2006, 49\u201356"},{"key":"3194_CR44","first-page":"3003","volume-title":"Proceedings of the 26th International Conference on Neural Information Processing Systems","author":"I Osband","year":"2013","unstructured":"Osband I, Russo D, Van Roy B. (More) efficient reinforcement learning via posterior sampling. In: Proceedings of the 26th International Conference on Neural Information Processing Systems. 2013, 3003\u20133011"},{"key":"3194_CR45","volume-title":"Go-explore: a new approach for hard-exploration problems","author":"A Ecoffet","year":"2019","unstructured":"Ecoffet A, Huizinga J, Lehman J, Stanley K O, Clune J. Go-explore: a new approach for hard-exploration problems. 2019, arXiv preprint arXiv: 1901.10995"},{"issue":"7847","key":"3194_CR46","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1038\/s41586-020-03157-9","volume":"590","author":"A Ecoffet","year":"2021","unstructured":"Ecoffet A, Huizinga J, Lehman J, Stanley K O, Clune J. First return, then explore. Nature, 2021, 590(7847): 580\u2013586","journal-title":"Nature"},{"key":"3194_CR47","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"M G Bellemare","year":"2013","unstructured":"Bellemare M G, Naddaf Y, Veness J, Bowling M. The arcade learning environment: An evaluation platform for general agents. Journal of Artificial Intelligence Research, 2013, 47: 253\u2013279","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"8","key":"3194_CR48","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1016\/j.jcss.2007.08.009","volume":"74","author":"A L Strehl","year":"2008","unstructured":"Strehl A L, Littman M L. An analysis of model-based interval estimation for Markov decision processes. Journal of Computer and System Sciences, 2008, 74(8): 1309\u20131331","journal-title":"Journal of Computer and System Sciences"},{"issue":"1","key":"3194_CR49","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/s10479-012-1064-y","volume":"208","author":"R Ortner","year":"2013","unstructured":"Ortner R. Adaptive aggregation for reinforcement learning in average reward Markov decision processes. Annals of Operations Research, 2013, 208(1): 321\u2013336","journal-title":"Annals of Operations Research"},{"key":"3194_CR50","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-642-32375-1_2","volume-title":"Intrinsically Motivated Learning in Natural and Artificial Systems","author":"A G Barto","year":"2013","unstructured":"Barto A G. Intrinsic motivation and reinforcement learning. In: Baldassarre G, Mirolli M, eds. Intrinsically Motivated Learning in Natural and Artificial Systems. Berlin: Springer, 2013, 17\u201347"},{"key":"3194_CR51","volume-title":"Structure and Direction in Thinking","author":"D E Berlyne","year":"1965","unstructured":"Berlyne D E. Structure and Direction in Thinking. Hoboken: Wiley, 1965"},{"key":"3194_CR52","volume-title":"Proceedings of the 21st International Conference on Machine Learning","author":"S Mannor","year":"2004","unstructured":"Mannor S, Menache I, Hoze A, Klein U. Dynamic abstraction in reinforcement learning via clustering. In: Proceedings of the 21st International Conference on Machine Learning. 2004"},{"key":"3194_CR53","first-page":"712","volume-title":"Proceedings of the IEEE International Conference on Tools with Artificial Intelligence","author":"N Tziortziotis","year":"2012","unstructured":"Tziortziotis N, Blekas K. A model based reinforcement learning approach using on-line clustering. In: Proceedings of the IEEE International Conference on Tools with Artificial Intelligence. 2012, 712\u2013718"},{"key":"3194_CR54","volume-title":"Proceedings of the 9th International Conference on Learning Representations","author":"T Wang","year":"2021","unstructured":"Wang T, Gupta T, Mahajan A, Peng B, Whiteson S, Zhang C J. RODE: learning roles to decompose multi-agent tasks. In: Proceedings of the 9th International Conference on Learning Representations. 2021"},{"key":"3194_CR55","first-page":"1989","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"F Christianos","year":"2021","unstructured":"Christianos F, Papoudakis G, Rahman A, Albrecht S V. Scaling multi-agent reinforcement learning with selective parameter sharing. In: Proceedings of the 38th International Conference on Machine Learning. 2021, 1989\u20131998"},{"key":"3194_CR56","first-page":"1830","volume-title":"Proceedings of the 25th International Joint Conference on Artificial Intelligence","author":"T Mandel","year":"2016","unstructured":"Mandel T, Liu Y E, Brunskill E, Popovic Z. Efficient Bayesian clustering for reinforcement learning. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence. 2016, 1830\u20131838"},{"key":"3194_CR57","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-642-35289-8_30","volume-title":"Neural Networks: Tricks of the Trade","author":"A Coates","year":"2012","unstructured":"Coates A, Ng A Y. Learning feature representations with K-means. In: Montavon G, Orr G B, M\u00fcller K R, eds. Neural Networks: Tricks of the Trade. 2nd ed. Berlin: Springer, 2012, 561\u2013580","edition":"2nd ed"},{"key":"3194_CR58","first-page":"1889","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"J Schulman","year":"2015","unstructured":"Schulman J, Levine S, Moritz P, Jordan M, Abbeel P. Trust region policy optimization. In: Proceedings of the 32nd International Conference on Machine Learning. 2015, 1889\u20131897"},{"key":"3194_CR59","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"Y Burda","year":"2019","unstructured":"Burda Y, Edwards H, Pathak D, Storkey A J, Darrell T, Efros A A. Large-scale study of curiosity-driven learning. In: Proceedings of the 7th International Conference on Learning Representations. 2019"},{"key":"3194_CR60","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"K Wang","year":"2023","unstructured":"Wang K, Zhou K, Kang B, Feng J, Yan S. Revisiting intrinsic reward for exploration in procedurally generated environments. In: Proceedings of the 11th International Conference on Learning Representations. 2023"},{"key":"3194_CR61","first-page":"380","volume-title":"Proceedings of the 34th Annual ACM Symposium on Theory of Computing","author":"M S Charikar","year":"2002","unstructured":"Charikar M S. Similarity estimation techniques from rounding algorithms. In: Proceedings of the 34th Annual ACM Symposium on Theory of Computing. 2002, 380\u2013388"},{"key":"3194_CR62","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","author":"C Voloshin","year":"2021","unstructured":"Voloshin C, Le H M, Jiang N, Yue Y. Empirical study of off-policy policy evaluation for reinforcement learning. In: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks. 2021"},{"key":"3194_CR63","first-page":"807","volume-title":"Proceedings of the 27th International Conference on Machine Learning","author":"V Nair","year":"2010","unstructured":"Nair V, Hinton G E. Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning. 2010, 807\u2013814"},{"key":"3194_CR64","volume-title":"Proceedings of the 30th International Conference on Machine Learning","author":"A L Maas","year":"2013","unstructured":"Maas A L, Hannun A Y, Ng A Y. Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of the 30th International Conference on Machine Learning. 2013"},{"issue":"86","key":"3194_CR65","first-page":"2579","volume":"9","author":"L Van Der Maaten","year":"2008","unstructured":"Van Der Maaten L, Hinton G. Visualizing data using t-SNE. Journal of Machine Learning Research, 2008, 9(86): 2579\u20132605","journal-title":"Journal of Machine Learning Research"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-024-3194-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11704-024-3194-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-024-3194-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T21:01:41Z","timestamp":1779310901000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11704-024-3194-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"references-count":65,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["3194"],"URL":"https:\/\/doi.org\/10.1007\/s11704-024-3194-1","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"6 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Competing interests\n                      The authors declare that they have no competing interests or financial conflicts to disclose.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"194313"}}