{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:20:31Z","timestamp":1723422031836},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/cec60901.2024.10611871","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:55:15Z","timestamp":1723139715000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Genetic Drift Regularization: On Preventing Actor Injection from Breaking Evolution Strategies"],"prefix":"10.1109","author":[{"given":"Paul","family":"Templier","sequence":"first","affiliation":[{"name":"Université de Toulouse,ISAE-SUPAERO,Toulouse,France"}]},{"given":"Emmanuel","family":"Rachelson","sequence":"additional","affiliation":[{"name":"Université de Toulouse,ISAE-SUPAERO,Toulouse,France"}]},{"given":"Antoine","family":"Cully","sequence":"additional","affiliation":[{"name":"Imperial College London,London,United Kingdom"}]},{"given":"Dennis G.","family":"Wilson","sequence":"additional","affiliation":[{"name":"Université de Toulouse,ISAE-SUPAERO,Toulouse,France"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/197"},{"journal-title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","year":"2017","author":"Salimans","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3569096"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5728"},{"journal-title":"Evolution-Guided Policy Gradient in Reinforcement Learning","year":"2018","author":"Khadka","key":"ref5"},{"journal-title":"Maximum Mutation Reinforcement Learning for Scalable Control","year":"2021","author":"Suri","key":"ref6"},{"volume-title":"An Introduction to Genetic Algorithms","year":"1998","author":"Mitchell","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-81283-5_8"},{"key":"ref9","article-title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","author":"Bellemare","year":"2012","journal-title":"CoRR, vol. abs\/1207.4708"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"key":"ref12","first-page":"15","author":"Marchesini","year":"2021","journal-title":"GENETIC SOFT UPDATES FOR POLICY EVOLUTION IN DEEP REINFORCEMENT LEARNING"},{"journal-title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","year":"2019","author":"Pourchot","key":"ref13"},{"journal-title":"Guiding Evolutionary Strategies with Off-Policy Actor-Critic","year":"2021","author":"Tang","key":"ref14"},{"key":"ref15","first-page":"4264","article-title":"Guided evolutionary strategies: Augmenting random search with surrogate gradients","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Maheswaranathan"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/205"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.10.134"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3449639.3459304"},{"key":"ref19","first-page":"1587","article-title":"Addressing Function Approx-imation Error in Actor-Critic Methods","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Fujimoto"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"Lillicrap","key":"ref20"},{"journal-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","year":"2018","author":"Haarnoja","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3583131.3590388"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3583133.3597059"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3583131.3590512"},{"journal-title":"Injecting External Solutions Into CMA-ES","year":"2011","author":"Hansen","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"journal-title":"ERL-Re 2: Efficient evolutionary reinforcement learning with shared state representation and individual policy representation","year":"2022","author":"Hao","key":"ref27"},{"journal-title":"Brax - A differentiable physics engine for large scale rigid body simulation","year":"2021","author":"Freeman","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3583133.3590733"},{"journal-title":"MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments","year":"2019","author":"Young","key":"ref30"},{"journal-title":"Proximal Policy Optimization Algorithms","year":"2017","author":"Schulman","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26099"},{"journal-title":"Accelerated quality-diversity for robotics through massive parallelism","year":"2022","author":"Lim","key":"ref33"}],"event":{"name":"2024 IEEE Congress on Evolutionary Computation (CEC)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 IEEE Congress on Evolutionary Computation (CEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609966\/10611750\/10611871.pdf?arnumber=10611871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:12:49Z","timestamp":1723349569000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611871\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/cec60901.2024.10611871","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}