{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:17:33Z","timestamp":1783037853698,"version":"3.54.6"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032076373","type":"print"},{"value":"9783032076380","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-07638-0_20","type":"book-chapter","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:22:37Z","timestamp":1763922157000},"page":"241-252","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Controllability Using Destination Channels with\u00a0Reward Navigation in\u00a0Multi-agent Systems"],"prefix":"10.1007","author":[{"given":"Gentoku","family":"Nakasone","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yamato","family":"Takahagi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshinari","family":"Motokawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuki","family":"Miyashita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toshiharu","family":"Sugawara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"20_CR1","unstructured":"Chen, V., Gupta, A., Marino, K.: Ask your humans: using human instructions to improve generalization in reinforcement learning. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=Y87Ri-GNHYu"},{"key":"20_CR2","unstructured":"Fried, D., et al.: Speaker-follower models for vision-and-language navigation. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS 2018, pp. 3318\u20133329 (2018)"},{"issue":"8","key":"20_CR3","doi-asserted-by":"publisher","first-page":"10902","DOI":"10.1109\/TITS.2021.3096998","volume":"23","author":"B Gangopadhyay","year":"2022","unstructured":"Gangopadhyay, B., Soora, H., Dasgupta, P.: Hierarchical program-triggered reinforcement learning agents for automated driving. IEEE Trans. Intell. Transp. Syst. 23(8), 10902\u201310911 (2022). https:\/\/doi.org\/10.1109\/TITS.2021.3096998","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"20_CR4","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, pp. 6382\u20136393. Curran Associates Inc., Red Hook (2017)"},{"key":"20_CR5","doi-asserted-by":"publisher","unstructured":"Motokawa, Y., Sugawara, T.: Strategy-following multi-agent deep reinforcement learning through external high-level instruction. Procedia Comput. Sci. 225, 2798\u20132807 (2023). https:\/\/doi.org\/10.1016\/j.procs.2023.10.272","DOI":"10.1016\/j.procs.2023.10.272"},{"key":"20_CR6","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1016\/j.compag.2018.12.048","volume":"157","author":"V Partel","year":"2019","unstructured":"Partel, V., Charan Kakarla, S., Ampatzidis, Y.: Development and evaluation of a low-cost and smart technology for precision weed management utilizing artificial intelligence. Comput. Electron. Agric. 157, 339\u2013350 (2019). https:\/\/doi.org\/10.1016\/j.compag.2018.12.048","journal-title":"Comput. Electron. Agric."},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming, 1st edn. Wiley, USA (1994)","DOI":"10.1002\/9780470316887"},{"key":"20_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.107698","volume":"206","author":"N Rai","year":"2023","unstructured":"Rai, N., Zhang, Y., Ram, B., Schumacher, L., Yellavajjala, R., Bajwa, S., Sun, X.: Applications of deep learning in precision weed management: a review. Comput. Electron. Agric. 206, 107698 (2023). https:\/\/doi.org\/10.1016\/j.compag.2023.107698","journal-title":"Comput. Electron. Agric."},{"key":"20_CR9","unstructured":"Rajeswaran, A., Ghotra, S., Ravindran, B., Levine, S.: EpOpt: learning robust neural network policies using model ensembles. In: Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI), pp. 3126\u20133132. AAAI Press (2017)"},{"key":"20_CR10","unstructured":"Rashid, T., Samvelyan, M., de\u00a0Witt, C.S., Farquhar, G., Foerster, J., Whiteson, S.: Qmix: monotonic value function factorisation for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4295\u20134304. PMLR (2018)"},{"key":"20_CR11","unstructured":"Ross, S., Gordon, G.J., Bagnell, D.: A reduction of imitation learning and structured prediction to no-regret online learning. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 627\u2013635. JMLR Workshop and Conference Proceedings (2011)"},{"key":"20_CR12","unstructured":"Saund, B., Held, D., Bajcsy, R.: A multi-step q-learning algorithm for constrained optimal stopping problems. In: Proceedings of the 30th Conference on Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"20_CR13","unstructured":"Sun, S.H., Wu, T.L., Lim, J.J.: Program guided agent. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=BkxUvnEYDH"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. In: Proceedings of the 16th International Conference on Autonomous Agents and MultiAgent Systems, pp. 2085\u20132087 (2017)","DOI":"10.65109\/JSRC7365"},{"key":"20_CR15","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1016\/j.eng.2022.05.017","volume":"21","author":"J Wu","year":"2022","unstructured":"Wu, J., Lv, C.: Toward human-in-the-loop AI: enhancing deep reinforcement learning via real-time human guidance for autonomous driving. Engineering 21, 240\u2013252 (2022). https:\/\/doi.org\/10.1016\/j.eng.2022.05.017","journal-title":"Engineering"},{"key":"20_CR16","unstructured":"Yang, Y., Inala, J.P., Bastani, O., Pu, Y., Solar-Lezama, A., Rinard, M.: Program synthesis guided reinforcement learning for partially observed environments. In: Advances in Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=QwNLVId9Df"},{"issue":"10","key":"20_CR17","doi-asserted-by":"publisher","first-page":"7086","DOI":"10.1109\/TII.2022.3143175","volume":"18","author":"WJ Yun","year":"2022","unstructured":"Yun, W.J., et al.: Cooperative multiagent deep reinforcement learning for reliable surveillance via autonomous multi-UAV control. IEEE Trans. Ind. Inform. 18(10), 7086\u20137096 (2022). https:\/\/doi.org\/10.1109\/TII.2022.3143175","journal-title":"IEEE Trans. Ind. Inform."}],"container-title":["Lecture Notes in Computer Science","Advances in Practical Applications of Agents, Multi-Agent Systems, and Computational Social Science: The PAAMS Collection"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07638-0_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:34:21Z","timestamp":1783035261000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07638-0_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"ISBN":["9783032076373","9783032076380"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07638-0_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"24 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAAMS Workshop","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Practical Applications of Agents and Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lille","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"paams2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/paams.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}