{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T13:50:25Z","timestamp":1777297825644,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","funder":[{"name":"National Key R&D Program of China","award":["2023YFB2703800"],"award-info":[{"award-number":["2023YFB2703800"]}]},{"name":"National Natural Science Foundation of China","award":["62372493"],"award-info":[{"award-number":["62372493"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792448","type":"proceedings-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T12:38:33Z","timestamp":1777293513000},"page":"5474-5483","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Alzo: Auto-Tuning with Reinforcement Learning for DAG-based Blockchains"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3676-1552","authenticated-orcid":false,"given":"Qiuyu","family":"Ding","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1652-7202","authenticated-orcid":false,"given":"Rongkai","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9220-2694","authenticated-orcid":false,"given":"Qinnan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China and Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6784-9709","authenticated-orcid":false,"given":"Zhen","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4646-7131","authenticated-orcid":false,"given":"Jieyi","family":"Long","sequence":"additional","affiliation":[{"name":"Theta Labs, Inc., San Jose, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7463-9922","authenticated-orcid":false,"given":"Mingchao","family":"Wan","sequence":"additional","affiliation":[{"name":"Beijing Academy of Blockchain and Edge Computing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1930-8534","authenticated-orcid":false,"given":"Sen","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Academy of Blockchain and Edge Computing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9708-0220","authenticated-orcid":false,"given":"Jin","family":"Dong","sequence":"additional","affiliation":[{"name":"Beijing Academy of Blockchain and Edge Computing, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/UPCON47278.2019.8980029"},{"key":"e_1_3_2_1_2_1","first-page":"469","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Alipourfard Omid","year":"2017","unstructured":"Omid Alipourfard, Hongqiang Harry Liu, Jianshu Chen, Shivaram Venkataraman, Minlan Yu, and Ming Zhang. 2017. CherryPick: Adaptively unearthing the best cloud configurations for big data analytics. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). 469-482."},{"key":"e_1_3_2_1_3_1","volume-title":"Miles Brundage, and Anil Anthony Bharath.","author":"Arulkumaran Kai","year":"2017","unstructured":"Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage, and Anil Anthony Bharath. 2017a. A brief survey of deep reinforcement learning. arXiv preprint arXiv:1708.05866 (2017)."},{"key":"e_1_3_2_1_4_1","volume-title":"Miles Brundage, and Anil Anthony Bharath.","author":"Arulkumaran Kai","year":"2017","unstructured":"Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage, and Anil Anthony Bharath. 2017b. Deep reinforcement learning: A brief survey. IEEE signal processing magazine, Vol. 34, 6 (2017), 26-38."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238175"},{"key":"e_1_3_2_1_6_1","volume-title":"Recent advances in hierarchical reinforcement learning. Discrete event dynamic systems","author":"Barto Andrew G","year":"2003","unstructured":"Andrew G Barto and Sridhar Mahadevan. 2003. Recent advances in hierarchical reinforcement learning. Discrete event dynamic systems, Vol. 13, 4 (2003), 341-379."},{"key":"e_1_3_2_1_7_1","volume-title":"Hierarchical reinforcement learning and decision making. Current opinion in neurobiology","author":"Botvinick Matthew Michael","year":"2012","unstructured":"Matthew Michael Botvinick. 2012. Hierarchical reinforcement learning and decision making. Current opinion in neurobiology, Vol. 22, 6 (2012), 956-962."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.14778\/3457390.3457404"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2981072"},{"key":"e_1_3_2_1_10_1","volume-title":"Conflux-rust: Rust implementation of Conflux protocol. https:\/\/github.com\/Conflux-Chain\/conflux-rust. Accessed: 2024-01-15.","author":"Network Conflux","year":"2024","unstructured":"Conflux Network. 2024. Conflux-rust: Rust implementation of Conflux protocol. https:\/\/github.com\/Conflux-Chain\/conflux-rust. Accessed: 2024-01-15."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064033"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403299"},{"key":"e_1_3_2_1_13_1","volume-title":"The Lagrangian relaxation method for solving integer programming problems. Management science","author":"Fisher Marshall L","year":"1981","unstructured":"Marshall L Fisher. 1981. The Lagrangian relaxation method for solving integer programming problems. Management science, Vol. 27, 1 (1981), 1-18."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1287\/inte.15.2.10"},{"key":"e_1_3_2_1_15_1","volume-title":"The Lagrangian relaxation method for solving integer programming problems. Management science","author":"Fisher Marshall L","year":"2004","unstructured":"Marshall L Fisher. 2004. The Lagrangian relaxation method for solving integer programming problems. Management science, Vol. 50, 12_supplement (2004), 1861-1871."},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. Pmlr","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning. Pmlr, 1861-1870."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3465084.3467905"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45586-8_4"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 2020 USENIX Annual Technical Conference. 515-528","author":"Li Chenxing","year":"2020","unstructured":"Chenxing Li, Peilun Li, Dong Zhou, Zhe Yang, Ming Wu, Guang Yang, Wei Xu, Fan Long, and Andrew Chi-Chih Yao. 2020. A decentralized blockchain with high throughput and fast confirmation. In Proceedings of the 2020 USENIX Annual Technical Conference. 515-528."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352129"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.14778\/3579075.3579076"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645386"},{"key":"e_1_3_2_1_23_1","volume-title":"Rt-dag: A dag-based blockchain supporting real-time transactions","author":"Liao Guoqiong","year":"2024","unstructured":"Guoqiong Liao, Hao Ding, Chuanling Zhong, and Yinxiang Lei. 2024. Rt-dag: A dag-based blockchain supporting real-time transactions. IEEE Internet of Things Journal (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2897805"},{"key":"e_1_3_2_1_25_1","volume-title":"Honglak Lee, and Sergey Levine.","author":"Nachum Ofir","year":"2018","unstructured":"Ofir Nachum, Shixiang Shane Gu, Honglak Lee, and Sergey Levine. 2018. Data-efficient hierarchical reinforcement learning. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_26_1","volume-title":"DSAC-C: Constrained Maximum Entropy for Robust Discrete Soft-Actor Critic. arXiv preprint arXiv:2310.17173","author":"Neo Dexter","year":"2023","unstructured":"Dexter Neo and Tsuhan Chen. 2023. DSAC-C: Constrained Maximum Entropy for Robust Discrete Soft-Actor Critic. arXiv preprint arXiv:2310.17173 (2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3272312"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"e_1_3_2_1_29_1","volume-title":"TidyBlock: A Novel Consensus Mechanism for DAG-based Blockchain in IoT","author":"Qu Xidi","year":"2024","unstructured":"Xidi Qu, Shengling Wang, Kun Li, Jianhui Huang, and Xiuzhen Cheng. 2024. TidyBlock: A Novel Consensus Mechanism for DAG-based Blockchain in IoT. IEEE Transactions on Mobile Computing (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321813"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3657284"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-30637-2_31"},{"key":"e_1_3_2_1_34_1","volume-title":"Iota Tangle: A cryptocurrency to communicate Internet-of-Things data. Future generation computer systems","author":"Silvano Wellington Fernandes","year":"2020","unstructured":"Wellington Fernandes Silvano and Roderval Marcelino. 2020. Iota Tangle: A cryptocurrency to communicate Internet-of-Things data. Future generation computer systems, Vol. 112 (2020), 307-319."},{"key":"e_1_3_2_1_35_1","volume-title":"Spectre: A fast and scalable cryptocurrency protocol. Cryptology ePrint Archive","author":"Sompolinsky Yonatan","year":"2016","unstructured":"Yonatan Sompolinsky, Yoad Lewenberg, and Aviv Zohar. 2016. Spectre: A fast and scalable cryptocurrency protocol. Cryptology ePrint Archive (2016)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3479722.3480990"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064029"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-020-09345-2"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3576899"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"e_1_3_2_1_41_1","volume-title":"Ryan Marcus, and Boon Thau Loo.","author":"Wu Chengru","year":"2022","unstructured":"Chengru Wu, Beomseok Mehta, Mohammad Javad Amiri, Ryan Marcus, and Boon Thau Loo. 2022. Adachain: A learned adaptive blockchain. arXiv preprint arXiv:2211.01580 (2022)."},{"key":"e_1_3_2_1_42_1","first-page":"26","article-title":"Hyperparameter optimization for machine learning models based on Bayesian optimization","volume":"17","author":"Wu Jia","year":"2019","unstructured":"Jia Wu, Xiu-Yun Chen, Hao Zhang, Li-Dong Xiong, Hang Lei, and Si-Hao Deng. 2019. Hyperparameter optimization for machine learning models based on Bayesian optimization. Journal of Electronic Science and Technology, Vol. 17, 1 (2019), 26-40.","journal-title":"Journal of Electronic Science and Technology"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00065"},{"key":"e_1_3_2_1_44_1","volume-title":"Fine Tuning for Dqn: Exploring Parameter Impacts on Cart Pole Performance. In ITM Web of Conferences","volume":"78","author":"Xu Ruoxi","year":"2025","unstructured":"Ruoxi Xu. 2025. Fine Tuning for Dqn: Exploring Parameter Impacts on Cart Pole Performance. In ITM Web of Conferences, Vol. 78. EDP Sciences, 01006."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00008"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404460"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3382743"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457291"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.12.031"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T13:03:50Z","timestamp":1777295030000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792448"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":49,"alternative-id":["10.1145\/3774904.3792448","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792448","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}