{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T16:11:23Z","timestamp":1776528683054,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T00:00:00Z","timestamp":1657324800000},"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":[[2022,7,9]]},"DOI":"10.1145\/3520304.3533980","type":"proceedings-article","created":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T15:29:44Z","timestamp":1658244584000},"page":"1966-1970","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Safety-informed mutations for evolutionary deep reinforcement learning"],"prefix":"10.1145","author":[{"given":"Enrico","family":"Marchesini","sequence":"first","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Amato","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Constrained Policy Optimization. In International Conference on Machine Learning (ICML).","author":"Achiam Joshua","year":"2017","unstructured":"Joshua Achiam, David Held, Aviv Tamar, and Pieter Abbeel. 2017. Constrained Policy Optimization. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_2_1","volume-title":"Constrained Markov Decision Processes","author":"Altman Eitan","unstructured":"Eitan Altman. 1999. Constrained Markov Decision Processes. In CRC Press."},{"key":"e_1_3_2_1_3_1","volume-title":"Conservative Safety Critics for Exploration. In International Conference on Learning Representations (ICLR).","author":"Bharadhwaj Homanga","year":"2021","unstructured":"Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart, Sergey Levine, Florian Shkurti, and Animesh Garg. 2021. Conservative Safety Critics for Exploration. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_4_1","volume-title":"Proximal Distilled Evolutionary Reinforcement Learning. In AAAI Conference on Artificial Intelligence.","author":"Bodnar Pietro Lio'","year":"2020","unstructured":"Pietro Lio' Bodnar, Ben Day. 2020. Proximal Distilled Evolutionary Reinforcement Learning. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_5_1","volume-title":"Conference on Neural Information Processing Systems (NeurIPS).","author":"Chow Yinlam","year":"2018","unstructured":"Yinlam Chow, Ofir Nachum, Edgar Duenez-Guzman, and Mohammad Ghavamzadeh. 2018. A Lyapunov-based Approach to Safe Reinforcement Learning. In Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_6_1","volume-title":"GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms. In International Conference on Machine Learning (ICML).","author":"Colas C\u00e9dric","year":"2018","unstructured":"C\u00e9dric Colas, Olivier Sigaud, and Pierre-Yves Oudeyer. 2018. GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_7_1","volume-title":"Conference on Neural Information Processing Systems (NeurIPS).","author":"Conti Edoardo","year":"2018","unstructured":"Edoardo Conti, Vashisht Madhavan, Felipe Petroski Such, Joel Lehman, Kenneth O. Stanley, and Jeff Clune. 2018. Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents. In Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence (Proceedings of Machine Learning Research","volume":"343","author":"Corsi Davide","year":"2021","unstructured":"Davide Corsi, Enrico Marchesini, and Alessandro Farinelli. 2021. Formal verification of neural networks for safety-critical tasks in deep reinforcement learning. In Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence (Proceedings of Machine Learning Research, Vol. 161), Cassio de Campos and Marloes H. Maathuis (Eds.). PMLR, 333--343."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2020.00062"},{"key":"e_1_3_2_1_10_1","unstructured":"Prafulla Dhariwal Christopher Hesse Oleg Klimov Alex Nichol Matthias Plappert Alec Radford John Schulman Szymon Sidor Yuhuai Wu and Peter Zhokhov. 2017. OpenAI Baselines. https:\/\/github.com\/openai\/baselines."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"David Fogel. 2006. Evolutionary computation - toward a new philosophy of machine intelligence (3. ed.).","DOI":"10.1002\/0471749214"},{"key":"e_1_3_2_1_12_1","volume-title":"IEEE International Conference on Robotics and Automation (ICRA).","author":"Gu S.","unstructured":"S. Gu, E. Holly, T. Lillicrap, and S. Levine. 2017. Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In IEEE International Conference on Robotics and Automation (ICRA)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"e_1_3_2_1_14_1","volume-title":"Diversity-Driven Exploration Strategy for Deep Reinforcement Learning. In Conference on Neural Information Processing Systems (NeurIPS).","author":"Hong Zhang-Wei","year":"2018","unstructured":"Zhang-Wei Hong, Tzu-Yun Shann, Shih-Yang Su, Yi-Hsiang Chang, and Chun-Yi Lee. 2018. Diversity-Driven Exploration Strategy for Deep Reinforcement Learning. In Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_15_1","volume-title":"Collaborative Evolutionary Reinforcement Learning. In International Conference on Machine Learning (ICML).","author":"Khadka Shauharda","year":"2019","unstructured":"Shauharda Khadka, Somdeb Majumdar, Tarek Nassar, Zach Dwiel, Evren Tumer, Santiago Miret, Yinyin Liu, and Kagan Tumer. 2019. Collaborative Evolutionary Reinforcement Learning. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_16_1","volume-title":"Evolutionary Reinforcement Learning. In Conference on Neural Information Processing Systems (NeurIPS).","author":"Khadka Shauharda","year":"2018","unstructured":"Shauharda Khadka and Kagan Tumer. 2018. Evolutionary Reinforcement Learning. In Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_17_1","volume-title":"Stanley","author":"Lehman Joel","year":"2018","unstructured":"Joel Lehman, Jay Chen, Jeff Clune, and Kenneth O. Stanley. 2018. Safe Mutations for Deep and Recurrent Neural Networks through Output Gradients. In GECCO."},{"key":"e_1_3_2_1_18_1","volume-title":"Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS).","author":"Lei Tai Ming Liu","year":"2017","unstructured":"Ming Liu Lei Tai, Giuseppe Paolo. 2017. Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1561\/2400000035"},{"key":"e_1_3_2_1_20_1","volume-title":"IPO: Interior-point Policy Optimization under Constraints. In AAAI.","author":"Liu Yongshuai","year":"2020","unstructured":"Yongshuai Liu, Jiaxin Ding, and Xin Liu. 2020. IPO: Interior-point Policy Optimization under Constraints. In AAAI."},{"key":"e_1_3_2_1_21_1","volume-title":"Genetic Soft Updates for Policy Evolution in Deep Reinforcement Learning. In International Conference on Learning Representations (ICLR).","author":"Marchesini Enrico","year":"2021","unstructured":"Enrico Marchesini, Davide Corsi, and Alessandro Farinelli. 2021. Genetic Soft Updates for Policy Evolution in Deep Reinforcement Learning. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_22_1","volume-title":"Exploring Safer Behaviors for Deep Reinforcement Learning. In AAAI Conference on Artificial Intelligence.","author":"Marchesini E.","unstructured":"E. Marchesini, D. Corsi, and A. Farinelli. 2022. Exploring Safer Behaviors for Deep Reinforcement Learning. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_23_1","volume-title":"Discrete Deep Reinforcement Learning for Mapless Navigation. In IEEE International Conference on Robotics and Automation (ICRA).","author":"Marchesini E.","unstructured":"E. Marchesini and A. Farinelli. 2020. Discrete Deep Reinforcement Learning for Mapless Navigation. In IEEE International Conference on Robotics and Automation (ICRA)."},{"key":"e_1_3_2_1_24_1","volume-title":"Genetic Deep Reinforcement Learning for Mapless Navigation. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS).","author":"Marchesini E.","unstructured":"E. Marchesini and A. Farinelli. 2020. Genetic Deep Reinforcement Learning for Mapless Navigation. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS)."},{"key":"e_1_3_2_1_25_1","volume-title":"Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigation. In 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Marchesini Enrico","unstructured":"Enrico Marchesini and Alessandro Farinelli. 2021. Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigation. In 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 4583--4588."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Jos\u00e8 Antonio Martin H. and Javier de Lope. 2009. Learning Autonomous Helicopter Flight with Evolutionary Reinforcement Learning. In Computer Aided Systems Theory.","DOI":"10.1007\/978-3-642-04772-5_11"},{"key":"e_1_3_2_1_27_1","volume-title":"Curriculum Learning for Safe Mapless Navigation. arXiv","author":"Marzari Luca","year":"2021","unstructured":"Luca Marzari, Davide Corsi, Enrico Marchesini, and Alessandro Farinelli. 2021. Curriculum Learning for Safe Mapless Navigation. arXiv (2021)."},{"key":"e_1_3_2_1_28_1","volume-title":"Playing Atari with Deep Reinforcement Learning. In Workshop of Conference on Neural Information Processing Systems (NeurIPS).","author":"Mnih V.","unstructured":"V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. In Workshop of Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_29_1","volume-title":"Training Feedforward Neural Networks Using Genetic Algorithms. In International Joint Conference on Artificial Intelligence (IJCAI).","author":"Montana D.","unstructured":"D. Montana and L. Davis. 1989. Training Feedforward Neural Networks Using Genetic Algorithms. In International Joint Conference on Artificial Intelligence (IJCAI)."},{"key":"e_1_3_2_1_30_1","volume-title":"Policy Gradient Assisted MAP-Elites. In GECCO '21","author":"Nilsson Olle","year":"2021","unstructured":"Olle Nilsson and Antoine Cully. 2021. Policy Gradient Assisted MAP-Elites. In GECCO '21."},{"key":"e_1_3_2_1_31_1","unstructured":"OpenAI Ilge Akkaya Marcin Andrychowicz Maciek Chociej Mateusz Litwin Bob McGrew Arthur Petron Alex Paino Matthias Plappert Glenn Powell Raphael Ribas Jonas Schneider Nikolas Tezak Jerry Tworek Peter Welinder Lilian Weng Qiming Yuan Wojciech Zaremba and Lei Zhang. 2019. Solving Rubik's Cube with a Robot Hand. In arXiv."},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Pourchot Alo\u00efs","year":"2019","unstructured":"Alo\u00efs Pourchot and Olivier Sigaud. 2019. CEM-RL: Combining evolutionary and gradient-based methods for policy search. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_33_1","unstructured":"Alex Ray Joshua Achiam and Dario Amodei. 2019. Benchmarking Safe Exploration in Deep Reinforcement Learning. In OpenAI."},{"key":"e_1_3_2_1_34_1","unstructured":"Olivier Sigaud. 2022. Combining Evolution and Deep Reinforcement Learning for Policy Search: a Survey. In arXiv."},{"key":"e_1_3_2_1_35_1","unstructured":"David Silver Aja Huang Chris Maddison and et al. 2018. Mastering the game of Go with deep neural networks and tree search.. In Nature."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"George Gaylord Simpson. 1953. The Baldwin Effect. In Evolution.","DOI":"10.2307\/2405746"},{"key":"e_1_3_2_1_37_1","unstructured":"Adam Stooke Joshua Achiam and Pieter Abbeel. 2020. Responsive Safety in Reinforcement Learning by PID Lagrangian Methods. In ICML."},{"key":"e_1_3_2_1_38_1","volume-title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning. In CoRR.","author":"Such Felipe Petroski","year":"2017","unstructured":"Felipe Petroski Such, Vashisht Madhavan, Edoardo Conti, Joel Lehman, Kenneth O. Stanley, and Jeff Clune. 2017. Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning. In CoRR."},{"key":"e_1_3_2_1_39_1","volume-title":"Barto","author":"Sutton Richard S.","year":"2018","unstructured":"Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. The MIT Press."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Brijen Thananjeyan Ashwin Balakrishna Ugo Rosolia Felix Li Rowan McAllister Joseph E. Gonzalez Sergey Levine Francesco Borrelli and Ken Goldberg. 2020. Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks. In RA-L.","DOI":"10.1109\/LRA.2020.2976272"}],"event":{"name":"GECCO '22: Genetic and Evolutionary Computation Conference","location":"Boston Massachusetts","acronym":"GECCO '22","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"]},"container-title":["Proceedings of the Genetic and Evolutionary Computation Conference Companion"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3520304.3533980","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3520304.3533980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:27Z","timestamp":1750186947000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3520304.3533980"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,9]]},"references-count":40,"alternative-id":["10.1145\/3520304.3533980","10.1145\/3520304"],"URL":"https:\/\/doi.org\/10.1145\/3520304.3533980","relation":{},"subject":[],"published":{"date-parts":[[2022,7,9]]},"assertion":[{"value":"2022-07-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}