{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T03:25:07Z","timestamp":1769916307337,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T00:00:00Z","timestamp":1689120000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,15]]},"DOI":"10.1145\/3583131.3590503","type":"proceedings-article","created":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T19:40:19Z","timestamp":1689190819000},"page":"138-146","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["MAP-Elites with Descriptor-Conditioned Gradients and Archive Distillation into a Single Policy"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4743-9494","authenticated-orcid":false,"given":"Maxence","family":"Faldor","sequence":"first","affiliation":[{"name":"Adaptive and Intelligent Robotics Lab, Imperial College London, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9476-2900","authenticated-orcid":false,"given":"F\u00e9lix","family":"Chalumeau","sequence":"additional","affiliation":[{"name":"InstaDeep, Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4601-2176","authenticated-orcid":false,"given":"Manon","family":"Flageat","sequence":"additional","affiliation":[{"name":"Adaptive and Intelligent Robotics Lab, Imperial College London, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3190-7073","authenticated-orcid":false,"given":"Antoine","family":"Cully","sequence":"additional","affiliation":[{"name":"Adaptive and Intelligent Robotics Lab, Imperial College London, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,12]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.03516"},{"key":"e_1_3_2_2_2_1","unstructured":"Felix Chalumeau Thomas Pierrot Valentin Mac\u00e9 Arthur Flajolet Karim Beguir Antoine Cully and Nicolas Perrin-Gilbert. 2022. Assessing Quality-Diversity Neuro-Evolution Algorithms Performance in Hard Exploration Problems. http:\/\/arxiv.org\/abs\/2211.13742 arXiv:2211.13742 [cs].  Felix Chalumeau Thomas Pierrot Valentin Mac\u00e9 Arthur Flajolet Karim Beguir Antoine Cully and Nicolas Perrin-Gilbert. 2022. Assessing Quality-Diversity Neuro-Evolution Algorithms Performance in Hard Exploration Problems. http:\/\/arxiv.org\/abs\/2211.13742 arXiv:2211.13742 [cs]."},{"key":"e_1_3_2_2_3_1","unstructured":"Konstantinos Chatzilygeroudis Antoine Cully Vassilis Vassiliades and Jean-Baptiste Mouret. 2020. Quality-Diversity Optimization: a novel branch of stochastic optimization. http:\/\/arxiv.org\/abs\/2012.04322 arXiv:2012.04322 [cs math stat].  Konstantinos Chatzilygeroudis Antoine Cully Vassilis Vassiliades and Jean-Baptiste Mouret. 2020. Quality-Diversity Optimization: a novel branch of stochastic optimization. http:\/\/arxiv.org\/abs\/2012.04322 arXiv:2012.04322 [cs math stat]."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.11.010"},{"key":"e_1_3_2_2_5_1","volume-title":"Scaling MAP-Elites to Deep Neuroevolution. CoRR abs\/2003.01825","author":"Colas C\u00e9dric","year":"2020","unstructured":"C\u00e9dric Colas , Joost Huizinga , Vashisht Madhavan , and Jeff Clune . 2020. Scaling MAP-Elites to Deep Neuroevolution. CoRR abs\/2003.01825 ( 2020 ), 67--75. arXiv:2003.01825 https:\/\/arxiv.org\/abs\/2003.01825 C\u00e9dric Colas, Joost Huizinga, Vashisht Madhavan, and Jeff Clune. 2020. Scaling MAP-Elites to Deep Neuroevolution. CoRR abs\/2003.01825 (2020), 67--75. arXiv:2003.01825 https:\/\/arxiv.org\/abs\/2003.01825"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14422"},{"key":"e_1_3_2_2_7_1","unstructured":"Antoine Cully and Yiannis Demiris. 2017. Quality and Diversity Optimization: A Unifying Modular Framework. http:\/\/arxiv.org\/abs\/1708.09251 arXiv:1708.09251 [cs].  Antoine Cully and Yiannis Demiris. 2017. Quality and Diversity Optimization: A Unifying Modular Framework. http:\/\/arxiv.org\/abs\/1708.09251 arXiv:1708.09251 [cs]."},{"key":"e_1_3_2_2_8_1","unstructured":"Adrien Ecoffet Joost Huizinga Joel Lehman Kenneth O. Stanley and Jeff Clune. 2021. Go-Explore: a New Approach for Hard-Exploration Problems. http:\/\/arxiv.org\/abs\/1901.10995 arXiv:1901.10995 [cs stat].  Adrien Ecoffet Joost Huizinga Joel Lehman Kenneth O. Stanley and Jeff Clune. 2021. Go-Explore: a New Approach for Hard-Exploration Problems. http:\/\/arxiv.org\/abs\/1901.10995 arXiv:1901.10995 [cs stat]."},{"key":"e_1_3_2_2_9_1","unstructured":"Benjamin Eysenbach Abhishek Gupta Julian Ibarz and Sergey Levine. 2018. Diversity is All You Need: Learning Skills without a Reward Function. http:\/\/arxiv.org\/abs\/1802.06070 arXiv:1802.06070 [cs].  Benjamin Eysenbach Abhishek Gupta Julian Ibarz and Sergey Levine. 2018. Diversity is All You Need: Learning Skills without a Reward Function. http:\/\/arxiv.org\/abs\/1802.06070 arXiv:1802.06070 [cs]."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577203"},{"key":"e_1_3_2_2_11_1","unstructured":"Manon Flageat Bryan Lim Luca Grillotti Maxime Allard Sim\u00f3n C. Smith and Antoine Cully. 2022. Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learning. http:\/\/arxiv.org\/abs\/2211.02193 arXiv:2211.02193 [cs].  Manon Flageat Bryan Lim Luca Grillotti Maxime Allard Sim\u00f3n C. Smith and Antoine Cully. 2022. Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learning. http:\/\/arxiv.org\/abs\/2211.02193 arXiv:2211.02193 [cs]."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.03894"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.10752"},{"key":"e_1_3_2_2_14_1","unstructured":"C. Daniel Freeman Erik Frey Anton Raichuk Sertan Girgin Igor Mordatch and Olivier Bachem. 2021. Brax - A Differentiable Physics Engine for Large Scale Rigid Body Simulation. http:\/\/arxiv.org\/abs\/2106.13281 arXiv:2106.13281 [cs].  C. Daniel Freeman Erik Frey Anton Raichuk Sertan Girgin Igor Mordatch and Olivier Bachem. 2021. Brax - A Differentiable Physics Engine for Large Scale Rigid Body Simulation. http:\/\/arxiv.org\/abs\/2106.13281 arXiv:2106.13281 [cs]."},{"key":"e_1_3_2_2_15_1","unstructured":"Scott Fujimoto Herke van Hoof and David Meger. 2018. Addressing Function Approximation Error in Actor-Critic Methods. http:\/\/arxiv.org\/abs\/1802.09477 arXiv:1802.09477 [cs stat].  Scott Fujimoto Herke van Hoof and David Meger. 2018. Addressing Function Approximation Error in Actor-Critic Methods. http:\/\/arxiv.org\/abs\/1802.09477 arXiv:1802.09477 [cs stat]."},{"key":"e_1_3_2_2_16_1","volume-title":"Danilo Jimenez Rezende, and Daan Wierstra","author":"Gregor Karol","year":"2016","unstructured":"Karol Gregor , Danilo Jimenez Rezende, and Daan Wierstra . 2016 . Variational Intrinsic Control . http:\/\/arxiv.org\/abs\/1611.07507 arXiv:1611.07507 [cs]. Karol Gregor, Danilo Jimenez Rezende, and Daan Wierstra. 2016. Variational Intrinsic Control. http:\/\/arxiv.org\/abs\/1611.07507 arXiv:1611.07507 [cs]."},{"key":"e_1_3_2_2_17_1","unstructured":"Shixiang Gu Ethan Holly Timothy Lillicrap and Sergey Levine. 2016. Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates. http:\/\/arxiv.org\/abs\/1610.00633 arXiv:1610.00633 [cs].  Shixiang Gu Ethan Holly Timothy Lillicrap and Sergey Levine. 2016. Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates. http:\/\/arxiv.org\/abs\/1610.00633 arXiv:1610.00633 [cs]."},{"key":"e_1_3_2_2_18_1","unstructured":"Tuomas Haarnoja Aurick Zhou Pieter Abbeel and Sergey Levine. 2018. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. http:\/\/arxiv.org\/abs\/1801.01290 arXiv:1801.01290 [cs stat].  Tuomas Haarnoja Aurick Zhou Pieter Abbeel and Sergey Levine. 2018. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. http:\/\/arxiv.org\/abs\/1801.01290 arXiv:1801.01290 [cs stat]."},{"key":"e_1_3_2_2_19_1","unstructured":"Nikolaus Hansen. 2016. The CMA Evolution Strategy: A Tutorial. http:\/\/arxiv.org\/abs\/1604.00772 arXiv:1604.00772 [cs stat].  Nikolaus Hansen. 2016. The CMA Evolution Strategy: A Tutorial. http:\/\/arxiv.org\/abs\/1604.00772 arXiv:1604.00772 [cs stat]."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.09846"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDL-EpiRob44920.2019"},{"key":"e_1_3_2_2_23_1","unstructured":"Saurabh Kumar Aviral Kumar Sergey Levine and Chelsea Finn. 2020. One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL. http:\/\/arxiv.org\/abs\/2010.14484 arXiv:2010.14484 [cs].  Saurabh Kumar Aviral Kumar Sergey Levine and Chelsea Finn. 2020. One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL. http:\/\/arxiv.org\/abs\/2010.14484 arXiv:2010.14484 [cs]."},{"key":"e_1_3_2_2_24_1","unstructured":"Timothy P. Lillicrap Jonathan J. Hunt Alexander Pritzel Nicolas Heess Tom Erez Yuval Tassa David Silver and Daan Wierstra. 2019. Continuous control with deep reinforcement learning. http:\/\/arxiv.org\/abs\/1509.02971 arXiv:1509.02971 [cs stat].  Timothy P. Lillicrap Jonathan J. Hunt Alexander Pritzel Nicolas Heess Tom Erez Yuval Tassa David Silver and Daan Wierstra. 2019. Continuous control with deep reinforcement learning. http:\/\/arxiv.org\/abs\/1509.02971 arXiv:1509.02971 [cs stat]."},{"key":"e_1_3_2_2_25_1","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. http:\/\/arxiv.org\/abs\/1312.5602 arXiv:1312.5602 [cs].  Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. http:\/\/arxiv.org\/abs\/1312.5602 arXiv:1312.5602 [cs]."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_2_27_1","unstructured":"Jean-Baptiste Mouret and Jeff Clune. 2015. Illuminating search spaces by mapping elites. http:\/\/arxiv.org\/abs\/1504.04909 arXiv:1504.04909 [cs q-bio].  Jean-Baptiste Mouret and Jeff Clune. 2015. Illuminating search spaces by mapping elites. http:\/\/arxiv.org\/abs\/1504.04909 arXiv:1504.04909 [cs q-bio]."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3449639.3459304"},{"key":"e_1_3_2_2_29_1","volume-title":"Pablo Samuel Castro, and Will Dabney","author":"Ostrovski Georg","year":"2021","unstructured":"Georg Ostrovski , Pablo Samuel Castro, and Will Dabney . 2021 . The Difficulty of Passive Learning in Deep Reinforcement Learning . http:\/\/arxiv.org\/abs\/2110.14020 arXiv:2110.14020 [cs]. Georg Ostrovski, Pablo Samuel Castro, and Will Dabney. 2021. The Difficulty of Passive Learning in Deep Reinforcement Learning. http:\/\/arxiv.org\/abs\/2110.14020 arXiv:2110.14020 [cs]."},{"key":"e_1_3_2_2_30_1","unstructured":"Thomas Pierrot and Arthur Flajolet. 2023. Evolving Populations of Diverse RL Agents with MAP-Elites. https:\/\/openreview.net\/forum?id=CBfYffLqWqb  Thomas Pierrot and Arthur Flajolet. 2023. Evolving Populations of Diverse RL Agents with MAP-Elites. https:\/\/openreview.net\/forum?id=CBfYffLqWqb"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512290.3528845"},{"key":"e_1_3_2_2_32_1","volume-title":"Stanley","author":"Pugh Justin K.","year":"2016","unstructured":"Justin K. Pugh , Lisa B. Soros , and Kenneth O . Stanley . 2016 . Quality Diversity : A New Frontier for Evolutionary Computation. Frontiers in Robotics and AI 3 (2016). https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2016.00040 Justin K. Pugh, Lisa B. Soros, and Kenneth O. Stanley. 2016. Quality Diversity: A New Frontier for Evolutionary Computation. Frontiers in Robotics and AI 3 (2016). https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2016.00040"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"1320","author":"Schaul Tom","year":"2015","unstructured":"Tom Schaul , Daniel Horgan , Karol Gregor , and David Silver . 2015 . Universal Value Function Approximators . In Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research , Vol. 37), Francis Bach and David Blei (Eds.). PMLR, Lille, France, 1312-- 1320 . https:\/\/proceedings.mlr.press\/v37\/schaul15.html Tom Schaul, Daniel Horgan, Karol Gregor, and David Silver. 2015. Universal Value Function Approximators. In Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 37), Francis Bach and David Blei (Eds.). PMLR, Lille, France, 1312--1320. https:\/\/proceedings.mlr.press\/v37\/schaul15.html"},{"key":"e_1_3_2_2_34_1","unstructured":"Archit Sharma Shixiang Gu Sergey Levine Vikash Kumar and Karol Hausman. 2020. Dynamics-Aware Unsupervised Discovery of Skills. http:\/\/arxiv.org\/abs\/1907.01657 arXiv:1907.01657 [cs stat].  Archit Sharma Shixiang Gu Sergey Levine Vikash Kumar and Karol Hausman. 2020. Dynamics-Aware Unsupervised Discovery of Skills. http:\/\/arxiv.org\/abs\/1907.01657 arXiv:1907.01657 [cs stat]."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"e_1_3_2_2_36_1","volume-title":"Proceedings of the 31st International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"395","author":"Silver David","year":"2014","unstructured":"David Silver , Guy Lever , Nicolas Heess , Thomas Degris , Daan Wierstra , and Martin Riedmiller . 2014 . Deterministic Policy Gradient Algorithms . In Proceedings of the 31st International Conference on Machine Learning (Proceedings of Machine Learning Research , Vol. 32), Eric P. Xing and Tony Jebara (Eds.). PMLR, Bejing, China, 387-- 395 . https:\/\/proceedings.mlr.press\/v32\/silver14.html David Silver, Guy Lever, Nicolas Heess, Thomas Degris, Daan Wierstra, and Martin Riedmiller. 2014. Deterministic Policy Gradient Algorithms. In Proceedings of the 31st International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 32), Eric P. Xing and Tony Jebara (Eds.). PMLR, Bejing, China, 387--395. https:\/\/proceedings.mlr.press\/v32\/silver14.html"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.02622"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2202.03666"},{"key":"e_1_3_2_2_39_1","unstructured":"Vassilis Vassiliades Konstantinos Chatzilygeroudis and Jean-Baptiste Mouret. 2017. Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithm. http:\/\/arxiv.org\/abs\/1610.05729 arXiv:1610.05729 [cs].  Vassilis Vassiliades Konstantinos Chatzilygeroudis and Jean-Baptiste Mouret. 2017. Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithm. http:\/\/arxiv.org\/abs\/1610.05729 arXiv:1610.05729 [cs]."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"}],"event":{"name":"GECCO '23: Genetic and Evolutionary Computation Conference","location":"Lisbon Portugal","acronym":"GECCO '23","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"]},"container-title":["Proceedings of the Genetic and Evolutionary Computation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583131.3590503","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583131.3590503","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:44Z","timestamp":1750178264000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583131.3590503"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,12]]},"references-count":40,"alternative-id":["10.1145\/3583131.3590503","10.1145\/3583131"],"URL":"https:\/\/doi.org\/10.1145\/3583131.3590503","relation":{},"subject":[],"published":{"date-parts":[[2023,7,12]]},"assertion":[{"value":"2023-07-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}