{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:12:36Z","timestamp":1750219956546,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T00:00:00Z","timestamp":1667433600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NSERC","award":["567794-2022"],"award-info":[{"award-number":["567794-2022"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,11,3]]},"DOI":"10.1145\/3561975.3562943","type":"proceedings-article","created":{"date-parts":[[2022,10,11]],"date-time":"2022-10-11T22:10:57Z","timestamp":1665526257000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning High-Risk High-Precision Motion Control"],"prefix":"10.1145","author":[{"given":"Nam Hee","family":"Kim","sequence":"first","affiliation":[{"name":"Aalto University, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Markus","family":"Kirjonen","sequence":"additional","affiliation":[{"name":"Aalto University, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Perttu","family":"H\u00e4m\u00e4l\u00e4inen","sequence":"additional","affiliation":[{"name":"Aalto University, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Trajectory optimization for full-body movements with complex contacts","author":"Al\u00a0Borno Mazen","year":"2012","unstructured":"Mazen Al\u00a0Borno , Martin De\u00a0Lasa , and Aaron Hertzmann . 2012. Trajectory optimization for full-body movements with complex contacts . IEEE transactions on visualization and computer graphics 19, 8( 2012 ), 1405\u20131414. Mazen Al\u00a0Borno, Martin De\u00a0Lasa, and Aaron Hertzmann. 2012. Trajectory optimization for full-body movements with complex contacts. IEEE transactions on visualization and computer graphics 19, 8(2012), 1405\u20131414."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v31i4.2312"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356536"},{"key":"e_1_3_2_1_5_1","unstructured":"Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016. Openai gym. arXiv preprint arXiv:1606.01540(2016).  Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016. Openai gym. arXiv preprint arXiv:1606.01540(2016)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848113"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"e_1_3_2_1_8_1","unstructured":"S\u00e9lim El\u00a0Mekki 2019. Recommender system for the billiard game. (2019).  S\u00e9lim El\u00a0Mekki 2019. Recommender system for the billiard game. (2019)."},{"key":"e_1_3_2_1_9_1","unstructured":"Ben Eysenbach Aviral Kumar and Abhishek Gupta. 2020. Reinforcement learning is supervised learning on optimized data. https:\/\/bair.berkeley.edu\/blog\/2020\/10\/13\/supervised-rl\/  Ben Eysenbach Aviral Kumar and Abhishek Gupta. 2020. Reinforcement learning is supervised learning on optimized data. https:\/\/bair.berkeley.edu\/blog\/2020\/10\/13\/supervised-rl\/"},{"key":"e_1_3_2_1_10_1","unstructured":"Katerina Fragkiadaki Pulkit Agrawal Sergey Levine and Jitendra Malik. 2015. Learning visual predictive models of physics for playing billiards. arXiv preprint arXiv:1511.07404(2015).  Katerina Fragkiadaki Pulkit Agrawal Sergey Levine and Jitendra Malik. 2015. Learning visual predictive models of physics for playing billiards. arXiv preprint arXiv:1511.07404(2015)."},{"key":"e_1_3_2_1_11_1","unstructured":"C.\u00a0Daniel 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:\/\/github.com\/google\/brax  C.\u00a0Daniel 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:\/\/github.com\/google\/brax"},{"key":"e_1_3_2_1_12_1","unstructured":"Dibya Ghosh Abhishek Gupta Ashwin Reddy Justin Fu Coline Devin Benjamin Eysenbach and Sergey Levine. 2019. Learning to reach goals via iterated supervised learning. arXiv preprint arXiv:1912.06088(2019).  Dibya Ghosh Abhishek Gupta Ashwin Reddy Justin Fu Coline Devin Benjamin Eysenbach and Sergey Levine. 2019. Learning to reach goals via iterated supervised learning. arXiv preprint arXiv:1912.06088(2019)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3233\/ICG-2005-28317"},{"key":"e_1_3_2_1_14_1","unstructured":"Tuomas Haarnoja Aurick Zhou Kristian Hartikainen George Tucker Sehoon Ha Jie Tan Vikash Kumar Henry Zhu Abhishek Gupta Pieter Abbeel 2018. Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905(2018).  Tuomas Haarnoja Aurick Zhou Kristian Hartikainen George Tucker Sehoon Ha Jie Tan Vikash Kumar Henry Zhu Abhishek Gupta Pieter Abbeel 2018. Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905(2018)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231618"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601218"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2767002"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3018187"},{"key":"e_1_3_2_1_19_1","volume-title":"Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES). Evolutionary computation 11, 1","author":"Hansen Nikolaus","year":"2003","unstructured":"Nikolaus Hansen , Sibylle\u00a0 D M\u00fcller , and Petros Koumoutsakos . 2003. Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES). Evolutionary computation 11, 1 ( 2003 ), 1\u201318. Nikolaus Hansen, Sibylle\u00a0D M\u00fcller, and Petros Koumoutsakos. 2003. Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES). Evolutionary computation 11, 1 (2003), 1\u201318."},{"key":"e_1_3_2_1_20_1","volume-title":"Difftaichi: Differentiable programming for physical simulation. arXiv preprint arXiv:1910.00935(2019).","author":"Hu Yuanming","year":"2019","unstructured":"Yuanming Hu , Luke Anderson , Tzu-Mao Li , Qi Sun , Nathan Carr , Jonathan Ragan-Kelley , and Fr\u00e9do Durand . 2019 . Difftaichi: Differentiable programming for physical simulation. arXiv preprint arXiv:1910.00935(2019). Yuanming Hu, Luke Anderson, Tzu-Mao Li, Qi Sun, Nathan Carr, Jonathan Ragan-Kelley, and Fr\u00e9do Durand. 2019. Difftaichi: Differentiable programming for physical simulation. arXiv preprint arXiv:1910.00935(2019)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3432907"},{"key":"e_1_3_2_1_22_1","unstructured":"Aviral Kumar Xue\u00a0Bin Peng and Sergey Levine. 2019. Reward-conditioned policies. arXiv preprint arXiv:1912.13465(2019).  Aviral Kumar Xue\u00a0Bin Peng and Sergey Levine. 2019. Reward-conditioned policies. arXiv preprint arXiv:1912.13465(2019)."},{"key":"e_1_3_2_1_23_1","volume-title":"Michiel van\u00a0de Panne, and Marie-Paule Cani","author":"Kwiatkowski Ariel","year":"2022","unstructured":"Ariel Kwiatkowski , Eduardo Alvarado , Vicky Kalogeiton , C\u00a0Karen Liu , Julien Pettr\u00e9 , Michiel van\u00a0de Panne, and Marie-Paule Cani . 2022 . A Survey on Reinforcement Learning Methods in Character Animation . arXiv preprint arXiv:2203.04735(2022). Ariel Kwiatkowski, Eduardo Alvarado, Vicky Kalogeiton, C\u00a0Karen Liu, Julien Pettr\u00e9, Michiel van\u00a0de Panne, and Marie-Paule Cani. 2022. A Survey on Reinforcement Learning Methods in Character Animation. arXiv preprint arXiv:2203.04735(2022)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-007-9172-7"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1992896.1992912"},{"key":"e_1_3_2_1_26_1","unstructured":"Liyuan Liu Haoming Jiang Pengcheng He Weizhu Chen Xiaodong Liu Jianfeng Gao and Jiawei Han. 2019. On the variance of the adaptive learning rate and beyond. arXiv preprint arXiv:1908.03265(2019).  Liyuan Liu Haoming Jiang Pengcheng He Weizhu Chen Xiaodong Liu Jianfeng Gao and Jiawei Han. 2019. On the variance of the adaptive learning rate and beyond. arXiv preprint arXiv:1908.03265(2019)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366173"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392474"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073707"},{"key":"e_1_3_2_1_30_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke , Sam Gross , Francisco Massa , Adam Lerer , James Bradbury , Gregory Chanan , Trevor Killeen , Zeming Lin , Natalia Gimelshein , Luca Antiga , 2019 . Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019). Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_31_1","volume-title":"Mcp: Learning composable hierarchical control with multiplicative compositional policies. Advances in Neural Information Processing Systems 32","author":"Peng Xue\u00a0Bin","year":"2019","unstructured":"Xue\u00a0Bin Peng , Michael Chang , Grace Zhang , Pieter Abbeel , and Sergey Levine . 2019 a. Mcp: Learning composable hierarchical control with multiplicative compositional policies. Advances in Neural Information Processing Systems 32 (2019). Xue\u00a0Bin Peng, Michael Chang, Grace Zhang, Pieter Abbeel, and Sergey Levine. 2019a. Mcp: Learning composable hierarchical control with multiplicative compositional policies. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_32_1","unstructured":"Xue\u00a0Bin Peng Aviral Kumar Grace Zhang and Sergey Levine. 2019b. Advantage-weighted regression: Simple and scalable off-policy reinforcement learning. arXiv preprint arXiv:1910.00177(2019).  Xue\u00a0Bin Peng Aviral Kumar Grace Zhang and Sergey Levine. 2019b. Advantage-weighted regression: Simple and scalable off-policy reinforcement learning. arXiv preprint arXiv:1910.00177(2019)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"e_1_3_2_1_34_1","unstructured":"Cristina Pinneri Shambhuraj Sawant Sebastian Blaes Jan Achterhold Joerg Stueckler Michal Rolinek and Georg Martius. 2020. Sample-efficient cross-entropy method for real-time planning. arXiv preprint arXiv:2008.06389(2020).  Cristina Pinneri Shambhuraj Sawant Sebastian Blaes Jan Achterhold Joerg Stueckler Michal Rolinek and Georg Martius. 2020. Sample-efficient cross-entropy method for real-time planning. arXiv preprint arXiv:2008.06389(2020)."},{"key":"e_1_3_2_1_35_1","volume-title":"Stable baselines3. GitHub repository","author":"Raffin Antonin","year":"2019","unstructured":"Antonin Raffin , Ashley Hill , Maximilian Ernestus , Adam Gleave , Anssi Kanervisto , and Noah Dormann . 2019. Stable baselines3. GitHub repository ( 2019 ). Antonin Raffin, Ashley Hill, Maximilian Ernestus, Adam Gleave, Anssi Kanervisto, and Noah Dormann. 2019. Stable baselines3. GitHub repository (2019)."},{"key":"e_1_3_2_1_36_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347(2017).  John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347(2017)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.04.011"},{"key":"e_1_3_2_1_38_1","unstructured":"Il\u2019ya\u00a0Meerovich Sobol\u2019. 1967. On the distribution of points in a cube and the approximate evaluation of integrals. Zhurnal Vychislitel\u2019noi Matematiki i Matematicheskoi Fiziki 7 4(1967) 784\u2013802.  Il\u2019ya\u00a0Meerovich Sobol\u2019. 1967. On the distribution of points in a cube and the approximate evaluation of integrals. Zhurnal Vychislitel\u2019noi Matematiki i Matematicheskoi Fiziki 7 4(1967) 784\u2013802."},{"key":"e_1_3_2_1_39_1","volume-title":"David Budden, Abbas Abdolmaleki","author":"Tassa Yuval","year":"2018","unstructured":"Yuval Tassa , Yotam Doron , Alistair Muldal , Tom Erez , Yazhe Li , Diego de\u00a0Las Casas , David Budden, Abbas Abdolmaleki , Josh Merel, Andrew Lefrancq , 2018 . Deepmind control suite. arXiv preprint arXiv:1801.00690(2018). Yuval Tassa, Yotam Doron, Alistair Muldal, Tom Erez, Yazhe Li, Diego de\u00a0Las Casas, David Budden, Abbas Abdolmaleki, Josh Merel, Andrew Lefrancq, 2018. Deepmind control suite. arXiv preprint arXiv:1801.00690(2018)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907001"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/54852.378507"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392381"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392381"}],"event":{"name":"MIG '22: ACM SIGGRAPH Conference on Motion, Interaction and Games","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"],"location":"Guanajuato Mexico","acronym":"MIG '22"},"container-title":["Proceedings of the 15th ACM SIGGRAPH Conference on Motion, Interaction and Games"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3561975.3562943","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3561975.3562943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:07Z","timestamp":1750182547000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3561975.3562943"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,3]]},"references-count":44,"alternative-id":["10.1145\/3561975.3562943","10.1145\/3561975"],"URL":"https:\/\/doi.org\/10.1145\/3561975.3562943","relation":{},"subject":[],"published":{"date-parts":[[2022,11,3]]},"assertion":[{"value":"2022-11-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}