{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T13:12:14Z","timestamp":1783775534262,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819228546","type":"print"},{"value":"9789819228522","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:00:00Z","timestamp":1783814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:00:00Z","timestamp":1783814400000},"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":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-2852-2_14","type":"book-chapter","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T12:29:33Z","timestamp":1783772973000},"page":"179-193","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Knowledge-Driven Dynamic Non-uniform Action Discretization Framework for\u00a0Value-Based Continuous Control"],"prefix":"10.1007","author":[{"given":"Shuxian","family":"Zhong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4365-0148","authenticated-orcid":false,"given":"Bi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,12]]},"reference":[{"key":"14_CR1","unstructured":"Chen, Y., Pan, Y., Hoffman, M., Huang, T., Mao, Y., Anguelov, D.: Learning by cheating: using simulation to train real-world driving policies. In: Conference on Robot Learning (CoRL), pp. 66\u201375 (2020)"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Hwangbo, J., et al.: Learning agile and dynamic motor skills for legged robots. Sci. Robot. 4(26), eaau5872 (2019)","DOI":"10.1126\/scirobotics.aau5872"},{"key":"14_CR3","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning arXiv:1509.02971 (2015)"},{"key":"14_CR4","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: ICML, pp. 1861\u20131870 (2018)"},{"key":"14_CR5","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal Policy Optimization Algorithms, arXiv:1707.06347 (2017)"},{"key":"14_CR6","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: ICML, pp. 1587\u20131596 (2018)"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Tang, Y., Agrawal, S.: Discretizing continuous action space for on-policy optimization. In: AAAI vol. 34(04), pp. 4537\u20134544 (2020)","DOI":"10.1609\/aaai.v34i04.6059"},{"key":"14_CR8","unstructured":"Seo, Y., Uru\u00e7, J., James, S.: Continuous control with coarse-to-fine reinforcement learning. In: CoRL, pp. 2866\u20132894 (2025)"},{"key":"14_CR9","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd ed. MIT Press (2018)"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Hoerger, M., Kurniawati, H., Kroese, D., Ye, N.: Adaptive Discretization using Voronoi Trees for Continuous-Action POMDPs (2022). arXiv:2209.05733","DOI":"10.1007\/978-3-031-21090-7_11"},{"key":"14_CR11","unstructured":"Jin, Y., Zhang, C., Wang, Z., Li, L.: Adaptive discretization for episodic reinforcement learning in metric spaces. In: NeurIPS, pp. 8883\u20138893 (2019)"},{"key":"14_CR12","unstructured":"Sinclair, A., Banerjee, S., Precup, D.: Adaptive discretization for model-based reinforcement learning. In NeurIPS, vol. 32 (2019)"},{"key":"14_CR13","unstructured":"Luo, J., Dong, P., Wu, J., Kumar, A., Geng, X., Levine, S.: Action-quantized offline reinforcement learning for robotic skill learning. In: CoRL, pp. 1348\u20131361 (2023)"},{"key":"14_CR14","first-page":"4530","volume":"162","author":"R Dadashi","year":"2022","unstructured":"Dadashi, R., et al.: Continuous control with action quantization from demonstrations. In ICML 162, 4530\u20134556 (2022)","journal-title":"In ICML"},{"key":"14_CR15","unstructured":"Asadi, K., Dalal, G., Hessel, M., Barreto, A., Hou, S., Silver, D.: RBF-DQN: approximate Optimal Control with Radial Basis Functions arXiv:1812.05251 (2018)"},{"key":"14_CR16","unstructured":"Gnad, D., Wabersich, K.P., Zeilinger, M.N.: Q3C: Structurally Maximizable Action-Value Functions for Continuous Control arXiv:2510.18828 (2025)"},{"key":"14_CR17","unstructured":"Wang, Z., Schaul, T., Hessel, M., Hasselt, H.V., Lanctot, M., Freitas, N.D.: Dueling network architectures for deep reinforcement learning. In: ICML, pp. 1995\u20132003 (2016)"},{"key":"14_CR18","unstructured":"Zanette, A., Agarwal, A.: Adaptive discretization for model-based reinforcement learning, In: NeurIPS, pp. 8593\u20138604 (2020)"},{"key":"14_CR19","unstructured":"Liu, J., Xu, H., Zhao, Y., Wang, C.: Particle-based adaptive discretization for continuous control using deep reinforcement learning. In: ICML, pp. 6212\u20136222 (2020)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Tavakoli, A., Pardo, F., Kormushev, P.: Action branching architectures for deep reinforcement learning. In: AAAI, pp. 5113\u20135120 (2018)","DOI":"10.1609\/aaai.v32i1.11798"},{"key":"14_CR21","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. In: Advances in Neural Information Processing Systems (NIPS), pp. 261\u2013269 (2015)"},{"key":"14_CR22","unstructured":"Hasselt, H.V., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: Advances in Neural Information Processing Systems (NIPS), pp. 2940\u20132948 (2015)"},{"key":"14_CR23","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press (2018)"},{"issue":"10","key":"14_CR24","first-page":"3991","volume":"31","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., Wang, Z., Liu, J., Sun, R.: Continuous control with swarm intelligence based value function approximation. IEEE Trans. Neural Netw. Learn. Syst. 31(10), 3991\u20134003 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-2852-2_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T12:29:35Z","timestamp":1783772975000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-2852-2_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,12]]},"ISBN":["9789819228546","9789819228522"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-2852-2_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,12]]},"assertion":[{"value":"12 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ksem2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem2026.rosc.org.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}