{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:36Z","timestamp":1750309476446,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T00:00:00Z","timestamp":1733875200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Science Foundation of China","award":["62202105"],"award-info":[{"award-number":["62202105"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,11]]},"DOI":"10.1145\/3678698.3678708","type":"proceedings-article","created":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T20:24:16Z","timestamp":1731961456000},"page":"1-1","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interactive Visual Analytics for Reward Function Setting of Reinforcement Learning: A Case Study of Soccer Games"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6194-0693","authenticated-orcid":false,"given":"Yihang","family":"Hu","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9403-1567","authenticated-orcid":false,"given":"Weixuan","family":"Song","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7096-7907","authenticated-orcid":false,"given":"Xingui","family":"Lai","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6511-4090","authenticated-orcid":false,"given":"Jie","family":"Li","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2690-3588","authenticated-orcid":false,"given":"Siming","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2024,12,11]]},"reference":[{"unstructured":"Marcin Andrychowicz Filip Wolski Alex Ray Jonas Schneider Rachel Fong Peter Welinder Bob McGrew Josh Tobin Pieter Abbeel and Wojciech Zaremba. 2017. Hindsight Experience Replay. CoRR abs\/1707.01495 (2017). arXiv:https:\/\/arXiv.org\/abs\/1707.01495http:\/\/arxiv.org\/abs\/1707.01495","key":"e_1_3_3_1_2_2"},{"doi-asserted-by":"crossref","unstructured":"Andrew\u00a0G. Barto Richard\u00a0S. Sutton and Charles\u00a0W. Anderson. 1983. Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Transactions on Systems Man and Cybernetics SMC-13 5 (1983) 834\u2013846.","key":"e_1_3_3_1_3_2","DOI":"10.1109\/TSMC.1983.6313077"},{"doi-asserted-by":"publisher","key":"e_1_3_3_1_4_2","DOI":"10.1609\/aaai.v37i5.25733"},{"doi-asserted-by":"crossref","unstructured":"Anqi Cao Xiao Xie Mingxu Zhou Hui Zhang Mingliang Xu and Yingcai Wu. 2024. Action-Evaluator: A Visualization Approach for Player Action Evaluation in Soccer. IEEE Transactions on Visualization and Computer Graphics 30 1 (2024) 880\u2013890.","key":"e_1_3_3_1_5_2","DOI":"10.1109\/TVCG.2023.3326524"},{"unstructured":"Paul Christiano Jan Leike Tom\u00a0B. Brown Miljan Martic Shane Legg and Dario Amodei. 2023. Deep reinforcement learning from human preferences. arxiv:https:\/\/arXiv.org\/abs\/1706.03741\u00a0[stat.ML]","key":"e_1_3_3_1_6_2"},{"doi-asserted-by":"crossref","unstructured":"Tom Decroos Jan Van\u00a0Haaren and Jesse Davis. 2018. Automatic Discovery of Tactics in Spatio-Temporal Soccer Match Data. 223\u2013232.","key":"e_1_3_3_1_7_2","DOI":"10.1145\/3219819.3219832"},{"unstructured":"Karol Kurach Anton Raichuk Piotr Stanczyk Michal Zajac Olivier Bachem Lasse Espeholt Carlos Riquelme Damien Vincent Marcin Michalski Olivier Bousquet and Sylvain Gelly. 2019. Google Research Football: A Novel Reinforcement Learning Environment. CoRR abs\/1907.11180 (2019). arXiv:https:\/\/arXiv.org\/abs\/1907.11180http:\/\/arxiv.org\/abs\/1907.11180","key":"e_1_3_3_1_8_2"},{"unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. Computer Science (2013).","key":"e_1_3_3_1_9_2"},{"unstructured":"Matthias Plappert Marcin Andrychowicz Alex Ray Bob McGrew Bowen Baker Glenn Powell Jonas Schneider Josh Tobin Maciek Chociej Peter Welinder Vikash Kumar and Wojciech Zaremba. 2018. Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research. CoRR abs\/1802.09464 (2018). arXiv:https:\/\/arXiv.org\/abs\/1802.09464http:\/\/arxiv.org\/abs\/1802.09464","key":"e_1_3_3_1_10_2"},{"doi-asserted-by":"crossref","unstructured":"Dean\u00a0A. Pomerleau. 1991. Efficient Training of Artificial Neural Networks for Autonomous Navigation. Neural Computation 3 1 (1991) 88\u201397.","key":"e_1_3_3_1_11_2","DOI":"10.1162\/neco.1991.3.1.88"},{"unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. CoRR abs\/1707.06347 (2017). arXiv:https:\/\/arXiv.org\/abs\/1707.06347http:\/\/arxiv.org\/abs\/1707.06347","key":"e_1_3_3_1_12_2"},{"doi-asserted-by":"crossref","unstructured":"Richard\u00a0S. Sutton and Andrew\u00a0G. Barto. 1998. Reinforcement Learning: An Introduction. IEEE Transactions on Neural Networks 9 5 (1998) 1054.","key":"e_1_3_3_1_13_2","DOI":"10.1109\/TNN.1998.712192"},{"unstructured":"Haoran Tang Rein Houthooft Davis Foote Adam Stooke Xi Chen Yan Duan John Schulman Filip\u00a0De Turck and Pieter Abbeel. 2016. #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning. CoRR abs\/1611.04717 (2016). arXiv:https:\/\/arXiv.org\/abs\/1611.04717http:\/\/arxiv.org\/abs\/1611.04717","key":"e_1_3_3_1_14_2"},{"unstructured":"Philip\u00a0S. Thomas and Emma Brunskill. 2017. Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines. CoRR abs\/1706.06643 (2017). arXiv:https:\/\/arXiv.org\/abs\/1706.06643http:\/\/arxiv.org\/abs\/1706.06643","key":"e_1_3_3_1_15_2"},{"doi-asserted-by":"crossref","unstructured":"C. Watkins J. Christopher and P. Dayan. 1992. Q-learning. Machine Learning 8 3 (1992) 279\u2013292.","key":"e_1_3_3_1_16_2","DOI":"10.1023\/A:1022676722315"}],"event":{"acronym":"VINCI 2024","name":"VINCI '24: The 17th International Symposium on Visual Information Communication and Interaction","location":"Hsinchu Taiwan"},"container-title":["Proceedings of the 17th International Symposium on Visual Information Communication and Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678698.3678708","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3678698.3678708","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:25Z","timestamp":1750295845000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678698.3678708"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,11]]},"references-count":15,"alternative-id":["10.1145\/3678698.3678708","10.1145\/3678698"],"URL":"https:\/\/doi.org\/10.1145\/3678698.3678708","relation":{},"subject":[],"published":{"date-parts":[[2024,12,11]]},"assertion":[{"value":"2024-12-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}