{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:14:35Z","timestamp":1750220075359,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,3,17]],"date-time":"2023-03-17T00:00:00Z","timestamp":1679011200000},"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":[[2023,3,17]]},"DOI":"10.1145\/3590003.3590101","type":"proceedings-article","created":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T18:22:56Z","timestamp":1685384576000},"page":"526-533","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on Constant Perturbation Strategy for Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4947-3151","authenticated-orcid":false,"given":"Jiamin","family":"Shen","sequence":"first","affiliation":[{"name":"Shenyang Aerospace University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4083-639X","authenticated-orcid":false,"given":"Li","family":"Xu","sequence":"additional","affiliation":[{"name":"Shenyang Aerospace University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0849-8555","authenticated-orcid":false,"given":"Xu","family":"Wan","sequence":"additional","affiliation":[{"name":"Shenyang Aircraft Design and Research Institute, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5569-9504","authenticated-orcid":false,"given":"Jixuan","family":"Chai","sequence":"additional","affiliation":[{"name":"Shenyang Aerospace University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8127-6292","authenticated-orcid":false,"given":"Chunlong","family":"Fan","sequence":"additional","affiliation":[{"name":"Shenyang Aerospace University, China"}]}],"member":"320","published-online":{"date-parts":[[2023,5,29]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Deep Reinforcement Learning for Robotic Manipulation - The state of the art. CoRR abs\/1701.08878","author":"Amarjyoti Smruti","year":"2017","unstructured":"Smruti Amarjyoti . 2017. Deep Reinforcement Learning for Robotic Manipulation - The state of the art. CoRR abs\/1701.08878 ( 2017 ). arXiv:1701.08878http:\/\/arxiv.org\/abs\/1701.08878 Smruti Amarjyoti. 2017. Deep Reinforcement Learning for Robotic Manipulation - The state of the art. CoRR abs\/1701.08878 (2017). arXiv:1701.08878http:\/\/arxiv.org\/abs\/1701.08878"},{"key":"e_1_3_2_1_2_1","volume-title":"Analysis and Improvement of Adversarial Training in DQN Agents With Adversarially-Guided Exploration (AGE). CoRR abs\/1906.01119","author":"Behzadan Vahid","year":"2019","unstructured":"Vahid Behzadan and William\u00a0 H. Hsu . 2019. Analysis and Improvement of Adversarial Training in DQN Agents With Adversarially-Guided Exploration (AGE). CoRR abs\/1906.01119 ( 2019 ). arXiv:1906.01119http:\/\/arxiv.org\/abs\/1906.01119 Vahid Behzadan and William\u00a0H. Hsu. 2019. Analysis and Improvement of Adversarial Training in DQN Agents With Adversarially-Guided Exploration (AGE). CoRR abs\/1906.01119 (2019). arXiv:1906.01119http:\/\/arxiv.org\/abs\/1906.01119"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-62416-7_19"},{"key":"e_1_3_2_1_4_1","volume-title":"Makes It Stronger. CoRR abs\/1712.09344","author":"Behzadan Vahid","year":"2017","unstructured":"Vahid Behzadan and Arslan Munir . 2017. Whatever Does Not Kill Deep Reinforcement Learning , Makes It Stronger. CoRR abs\/1712.09344 ( 2017 ). arXiv:1712.09344http:\/\/arxiv.org\/abs\/1712.09344 Vahid Behzadan and Arslan Munir. 2017. Whatever Does Not Kill Deep Reinforcement Learning, Makes It Stronger. CoRR abs\/1712.09344 (2017). arXiv:1712.09344http:\/\/arxiv.org\/abs\/1712.09344"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99229-7_34"},{"key":"e_1_3_2_1_6_1","volume-title":"Dota 2 with Large Scale Deep Reinforcement Learning. CoRR abs\/1912.06680","author":"Berner Christopher","year":"2019","unstructured":"Christopher Berner , Greg Brockman , Brooke Chan , and Vicki Cheung . 2019. Dota 2 with Large Scale Deep Reinforcement Learning. CoRR abs\/1912.06680 ( 2019 ). arXiv:1912.06680http:\/\/arxiv.org\/abs\/1912.06680 Christopher Berner, Greg Brockman, Brooke Chan, and Vicki Cheung. 2019. Dota 2 with Large Scale Deep Reinforcement Learning. CoRR abs\/1912.06680 (2019). arXiv:1912.06680http:\/\/arxiv.org\/abs\/1912.06680"},{"key":"e_1_3_2_1_7_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 . 2016. Open AI Gym . CoRR abs\/1606.01540 ( 2016 ). arXiv:1606.01540http:\/\/arxiv.org\/abs\/1606.01540 Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. 2016. OpenAI Gym. CoRR abs\/1606.01540 (2016). arXiv:1606.01540http:\/\/arxiv.org\/abs\/1606.01540"},{"key":"e_1_3_2_1_8_1","volume-title":"Caicedo and Svetlana Lazebnik","author":"C.","year":"2015","unstructured":"Juan\u00a0 C. Caicedo and Svetlana Lazebnik . 2015 . Active Object Localization with Deep Reinforcement Learning. CoRR abs\/1511.06015 (2015). arXiv:1511.06015http:\/\/arxiv.org\/abs\/1511.06015 Juan\u00a0C. Caicedo and Svetlana Lazebnik. 2015. Active Object Localization with Deep Reinforcement Learning. CoRR abs\/1511.06015 (2015). arXiv:1511.06015http:\/\/arxiv.org\/abs\/1511.06015"},{"key":"e_1_3_2_1_9_1","volume-title":"3rd International Conference on Learning Representations, ICLR","author":"Goodfellow J.","year":"2015","unstructured":"Ian\u00a0 J. Goodfellow , Jonathon Shlens , and Christian Szegedy . 2015. Explaining and Harnessing Adversarial Examples . In 3rd International Conference on Learning Representations, ICLR 2015 , San Diego, CA , USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds .). http:\/\/arxiv.org\/abs\/1412.6572 Ian\u00a0J. Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and Harnessing Adversarial Examples. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1412.6572"},{"key":"e_1_3_2_1_10_1","volume-title":"Distributed Prioritized Experience Replay. CoRR abs\/1803.00933","author":"Horgan Dan","year":"2018","unstructured":"Dan Horgan , John Quan , David Budden , Gabriel Barth-Maron , Matteo Hessel , Hado van Hasselt , and David Silver . 2018. Distributed Prioritized Experience Replay. CoRR abs\/1803.00933 ( 2018 ). arXiv:1803.00933http:\/\/arxiv.org\/abs\/1803.00933 Dan Horgan, John Quan, David Budden, Gabriel Barth-Maron, Matteo Hessel, Hado van Hasselt, and David Silver. 2018. Distributed Prioritized Experience Replay. CoRR abs\/1803.00933 (2018). arXiv:1803.00933http:\/\/arxiv.org\/abs\/1803.00933"},{"key":"e_1_3_2_1_11_1","volume-title":"5th International Conference on Learning Representations, ICLR","author":"Huang H.","year":"2017","unstructured":"Sandy\u00a0 H. Huang , Nicolas Papernot , Ian\u00a0 J. Goodfellow , Yan Duan , and Pieter Abbeel . 2017. Adversarial Attacks on Neural Network Policies . In 5th International Conference on Learning Representations, ICLR 2017 , Toulon, France, April 24-26, 2017, Workshop Track Proceedings. OpenReview .net. https:\/\/openreview.net\/forum?id=ryvlRyBKl Sandy\u00a0H. Huang, Nicolas Papernot, Ian\u00a0J. Goodfellow, Yan Duan, and Pieter Abbeel. 2017. Adversarial Attacks on Neural Network Policies. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Workshop Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=ryvlRyBKl"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.16383\/j.aas.c200166"},{"key":"e_1_3_2_1_13_1","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Workshop Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=BJcib5mFe","author":"Kos Jernej","year":"2017","unstructured":"Jernej Kos and Dawn Song . 2017 . Delving into adversarial attacks on deep policies . In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Workshop Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=BJcib5mFe Jernej Kos and Dawn Song. 2017. Delving into adversarial attacks on deep policies. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Workshop Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=BJcib5mFe"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/525"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_16_1","volume-title":"Playing Atari with Deep Reinforcement Learning. CoRR abs\/1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih , Koray Kavukcuoglu , David Silver , Alex Graves , Ioannis Antonoglou , Daan Wierstra , and Martin\u00a0 A. Riedmiller . 2013. Playing Atari with Deep Reinforcement Learning. CoRR abs\/1312.5602 ( 2013 ). Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin\u00a0A. Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. CoRR abs\/1312.5602 (2013)."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016(JMLR Workshop and Conference Proceedings, Vol.\u00a048)","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih , Adri\u00a0Puigdom nech Badia , Mehdi Mirza , Alex Graves , Timothy\u00a0 P. Lillicrap , Tim Harley , David Silver , and Koray Kavukcuoglu . 2016 . Asynchronous Methods for Deep Reinforcement Learning . In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016(JMLR Workshop and Conference Proceedings, Vol.\u00a048) , Maria-Florina Balcan and Kilian\u00a0Q. Weinberger (Eds.). JMLR.org , 1928\u20131937. http:\/\/proceedings.mlr.press\/v48\/mniha16.html Volodymyr Mnih, Adri\u00a0Puigdom nech Badia, Mehdi Mirza, Alex Graves, Timothy\u00a0P. Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous Methods for Deep Reinforcement Learning. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016(JMLR Workshop and Conference Proceedings, Vol.\u00a048), Maria-Florina Balcan and Kilian\u00a0Q. Weinberger (Eds.). JMLR.org, 1928\u20131937. http:\/\/proceedings.mlr.press\/v48\/mniha16.html"},{"key":"e_1_3_2_1_18_1","volume-title":"Action-Conditional Video Prediction using Deep Networks in Atari Games. CoRR abs\/1507.08750","author":"Oh Junhyuk","year":"2015","unstructured":"Junhyuk Oh , Xiaoxiao Guo , Honglak Lee , Richard\u00a0 L. Lewis , and Satinder Singh . 2015. Action-Conditional Video Prediction using Deep Networks in Atari Games. CoRR abs\/1507.08750 ( 2015 ). arXiv:1507.08750http:\/\/arxiv.org\/abs\/1507.08750 Junhyuk Oh, Xiaoxiao Guo, Honglak Lee, Richard\u00a0L. Lewis, and Satinder Singh. 2015. Action-Conditional Video Prediction using Deep Networks in Atari Games. CoRR abs\/1507.08750 (2015). arXiv:1507.08750http:\/\/arxiv.org\/abs\/1507.08750"},{"key":"e_1_3_2_1_19_1","volume-title":"An overview of gradient descent optimization algorithms. CoRR abs\/1609.04747","author":"Ruder Sebastian","year":"2016","unstructured":"Sebastian Ruder . 2016. An overview of gradient descent optimization algorithms. CoRR abs\/1609.04747 ( 2016 ). arXiv:1609.04747http:\/\/arxiv.org\/abs\/1609.04747 Sebastian Ruder. 2016. An overview of gradient descent optimization algorithms. CoRR abs\/1609.04747 (2016). arXiv:1609.04747http:\/\/arxiv.org\/abs\/1609.04747"},{"key":"e_1_3_2_1_20_1","volume-title":"Trust Region Policy Optimization. CoRR abs\/1502.05477","author":"Schulman John","year":"2015","unstructured":"John Schulman , Sergey Levine , Philipp Moritz , Michael\u00a0 I. Jordan , and Pieter Abbeel . 2015. Trust Region Policy Optimization. CoRR abs\/1502.05477 ( 2015 ). arXiv:1502.05477http:\/\/arxiv.org\/abs\/1502.05477 John Schulman, Sergey Levine, Philipp Moritz, Michael\u00a0I. Jordan, and Pieter Abbeel. 2015. Trust Region Policy Optimization. CoRR abs\/1502.05477 (2015). arXiv:1502.05477http:\/\/arxiv.org\/abs\/1502.05477"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6047"},{"key":"e_1_3_2_1_23_1","volume-title":"Deep Reinforcement Learning with Double Q-learning. CoRR abs\/1509.06461","author":"van Hasselt Hado","year":"2015","unstructured":"Hado van Hasselt , Arthur Guez , and David Silver . 2015. Deep Reinforcement Learning with Double Q-learning. CoRR abs\/1509.06461 ( 2015 ). arXiv:1509.06461http:\/\/arxiv.org\/abs\/1509.06461 Hado van Hasselt, Arthur Guez, and David Silver. 2015. Deep Reinforcement Learning with Double Q-learning. CoRR abs\/1509.06461 (2015). arXiv:1509.06461http:\/\/arxiv.org\/abs\/1509.06461"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6086"},{"key":"e_1_3_2_1_25_1","volume-title":"Dueling Network Architectures for Deep Reinforcement Learning. CoRR abs\/1511.06581","author":"Wang Ziyu","year":"2015","unstructured":"Ziyu Wang , Nando de Freitas , and Marc Lanctot . 2015. Dueling Network Architectures for Deep Reinforcement Learning. CoRR abs\/1511.06581 ( 2015 ). arXiv:1511.06581http:\/\/arxiv.org\/abs\/1511.06581 Ziyu Wang, Nando de Freitas, and Marc Lanctot. 2015. Dueling Network Architectures for Deep Reinforcement Learning. CoRR abs\/1511.06581 (2015). arXiv:1511.06581http:\/\/arxiv.org\/abs\/1511.06581"},{"key":"e_1_3_2_1_26_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Zhang Huan","year":"2020","unstructured":"Huan Zhang , Hongge Chen , Chaowei Xiao , Bo Li , Mingyan Liu , Duane\u00a0 S. Boning , and Cho-Jui Hsieh . 2020 . Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations . In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 , NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc\u2019Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/f0eb6568ea114ba6e293f903c34d7488-Abstract.html Huan Zhang, Hongge Chen, Chaowei Xiao, Bo Li, Mingyan Liu, Duane\u00a0S. Boning, and Cho-Jui Hsieh. 2020. Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc\u2019Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/f0eb6568ea114ba6e293f903c34d7488-Abstract.html"}],"event":{"name":"CACML 2023: 2023 2nd Asia Conference on Algorithms, Computing and Machine Learning","acronym":"CACML 2023","location":"Shanghai China"},"container-title":["Proceedings of the 2023 2nd Asia Conference on Algorithms, Computing and Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3590003.3590101","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3590003.3590101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:17Z","timestamp":1750183757000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3590003.3590101"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,17]]},"references-count":26,"alternative-id":["10.1145\/3590003.3590101","10.1145\/3590003"],"URL":"https:\/\/doi.org\/10.1145\/3590003.3590101","relation":{},"subject":[],"published":{"date-parts":[[2023,3,17]]},"assertion":[{"value":"2023-05-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}