{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:19:13Z","timestamp":1750220353275,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":10,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,26]],"date-time":"2020-06-26T00:00:00Z","timestamp":1593129600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,26]]},"DOI":"10.1145\/3430199.3430210","type":"proceedings-article","created":{"date-parts":[[2020,12,22]],"date-time":"2020-12-22T02:08:59Z","timestamp":1608602939000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Application Research of Model-Free Reinforcement Learning under the Condition of Conditional Transfer Function with Coupling Factors"],"prefix":"10.1145","author":[{"given":"Xiaoya","family":"Yang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youtian","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Institute of Software Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,12,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"CoRR abs\/1606.01540","author":"Brockman Greg","year":"2016","unstructured":"Greg Brockman , Vicki Cheung , Ludwig Pettersson , Jonas Schneider , John Schulman , Jie Tang , and Wojciech Zaremba . 2016a. Open AI Gym . CoRR abs\/1606.01540 ( 2016 ). arXiv:1606.01540. Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. 2016a. OpenAI Gym. CoRR abs\/1606.01540 (2016). arXiv:1606.01540."},{"key":"e_1_3_2_1_2_1","first-page":"1889","volume-title":"International Conference on Machine Learning","author":"Schulman John","year":"2015","unstructured":"John Schulman , Sergey Levine , Pieter Abbeel , Michael Jordan , and Philipp Moritz . Trust region policy optimization . In International Conference on Machine Learning , pages 1889 -- 1897 , 2015 . John Schulman, Sergey Levine, Pieter Abbeel, Michael Jordan, and Philipp Moritz. Trust region policy optimization. In International Conference on Machine Learning, pages 1889--1897, 2015."},{"key":"e_1_3_2_1_3_1","volume-title":"Proximal Policy Optimization Algorithms. ArXiv eprints","author":"Schulman J.","year":"2017","unstructured":"J. Schulman , F. Wolski , P. Dhariwal , A. Radford , and O. Klimov . Proximal Policy Optimization Algorithms. ArXiv eprints , 2017 . J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov. Proximal Policy Optimization Algorithms. ArXiv eprints, 2017."},{"volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","year":"2013","key":"e_1_3_2_1_4_1","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller, M . Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 , 2013 . Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller, M. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602, 2013."},{"key":"e_1_3_2_1_5_1","first-page":"5","article-title":"Reinforcement Learning","volume":"9","author":"Sutton R. S.","year":"1998","unstructured":"R. S. Sutton and A. G. Barto . 1998 . Reinforcement Learning : An Introduction. Trans. Neur. Netw. 9 , 5 (September 1998), 1054. DOI:https:\/\/doi.org\/10.1109\/TNN.1998.71219. 10.1109\/TNN.1998.71219 R. S. Sutton and A. G. Barto. 1998. Reinforcement Learning: An Introduction. Trans. Neur. Netw. 9, 5 (September 1998), 1054. DOI:https:\/\/doi.org\/10.1109\/TNN.1998.71219.","journal-title":"An Introduction. Trans. Neur. Netw."},{"key":"e_1_3_2_1_6_1","volume-title":"Policy gradient methods for reinforcement learning with function approximation. Neural Information Processing Systems, 13","author":"Sutton R.","year":"2000","unstructured":"R. Sutton , D. McAllester , S. Singh , and Y. Mansour . Policy gradient methods for reinforcement learning with function approximation. Neural Information Processing Systems, 13 , 2000 . R. Sutton, D. McAllester, S. Singh, and Y. Mansour. Policy gradient methods for reinforcement learning with function approximation. Neural Information Processing Systems, 13, 2000."},{"volume-title":"Proceedings of the International Conference on Learning Representations","year":"2016","key":"e_1_3_2_1_7_1","unstructured":"Schaul, Tom, Quan, John, Antonoglou, Ioannis, and Silver, David. Prioritized experience replay . In Proceedings of the International Conference on Learning Representations , 2016 . Schaul, Tom, Quan, John, Antonoglou, Ioannis, and Silver, David. Prioritized experience replay. In Proceedings of the International Conference on Learning Representations, 2016."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/2980539.2980738"},{"key":"e_1_3_2_1_9_1","volume-title":"Off-policy actor-critic. arXiv preprint arXiv:1205.4839","author":"Degris Thomas","year":"2012","unstructured":"Thomas Degris , Martha White , and Richard S Sutton . 2012. Off-policy actor-critic. arXiv preprint arXiv:1205.4839 ( 2012 ). Thomas Degris, Martha White, and Richard S Sutton. 2012. Off-policy actor-critic. arXiv preprint arXiv:1205.4839 (2012)."},{"key":"e_1_3_2_1_10_1","volume-title":"Actor-critic algorithms. Advances in Neural Information Processing Systems, 12","author":"Konda V.","year":"2000","unstructured":"V. Konda and J. Tsitsiklis . Actor-critic algorithms. Advances in Neural Information Processing Systems, 12 , 2000 . V. Konda and J. Tsitsiklis. Actor-critic algorithms. Advances in Neural Information Processing Systems, 12, 2000."}],"event":{"name":"AIPR 2020: 2020 3rd International Conference on Artificial Intelligence and Pattern Recognition","acronym":"AIPR 2020","location":"Xiamen China"},"container-title":["Proceedings of the 2020 3rd International Conference on Artificial Intelligence and Pattern Recognition"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3430199.3430210","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3430199.3430210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:17:13Z","timestamp":1750191433000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3430199.3430210"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,26]]},"references-count":10,"alternative-id":["10.1145\/3430199.3430210","10.1145\/3430199"],"URL":"https:\/\/doi.org\/10.1145\/3430199.3430210","relation":{},"subject":[],"published":{"date-parts":[[2020,6,26]]},"assertion":[{"value":"2020-12-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}