{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:55:32Z","timestamp":1784300132840,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,11,8]],"date-time":"2018-11-08T00:00:00Z","timestamp":1541635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11,8]]},"DOI":"10.1145\/3274247.3274506","type":"proceedings-article","created":{"date-parts":[[2018,11,6]],"date-time":"2018-11-06T13:36:57Z","timestamp":1541511417000},"page":"1-10","source":"Crossref","is-referenced-by-count":67,"title":["Physics-based motion capture imitation with deep reinforcement learning"],"prefix":"10.1145","author":[{"given":"Nuttapong","family":"Chentanez","sequence":"first","affiliation":[{"name":"Chulalongkorn University, Bangkok, Thailand and NVIDIA Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miles","family":"Macklin","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Viktor","family":"Makoviychuk","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Jeschke","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,11,8]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"{n. d.}. CMU Motion Capture Database. http:\/\/mocap.cs.cmu.edu\/.  {n. d.}. CMU Motion Capture Database. http:\/\/mocap.cs.cmu.edu\/."},{"key":"e_1_3_2_2_2_1","unstructured":"{n. d.}. RoboSchool. https:\/\/github.com\/openai\/roboschool.  {n. d.}. RoboSchool. https:\/\/github.com\/openai\/roboschool."},{"key":"e_1_3_2_2_3_1","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg S. Corrado Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Ian Goodfellow Andrew Harp Geoffrey Irving Michael Isard Yangqing Jia Rafal Jozefowicz Lukasz Kaiser Manjunath Kudlur Josh Levenberg Dandelion Man\u00e9 Rajat Monga Sherry Moore Derek Murray Chris Olah Mike Schuster Jonathon Shlens Benoit Steiner Ilya Sutskever Kunal Talwar Paul Tucker Vincent Vanhoucke Vijay Vasudevan Fernanda Vi\u00e9gas Oriol Vinyals Pete Warden Martin Wattenberg Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. https:\/\/www.tensorflow.org\/ Software available from tensorflow.org.  Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg S. Corrado Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Ian Goodfellow Andrew Harp Geoffrey Irving Michael Isard Yangqing Jia Rafal Jozefowicz Lukasz Kaiser Manjunath Kudlur Josh Levenberg Dandelion Man\u00e9 Rajat Monga Sherry Moore Derek Murray Chris Olah Mike Schuster Jonathon Shlens Benoit Steiner Ilya Sutskever Kunal Talwar Paul Tucker Vincent Vanhoucke Vijay Vasudevan Fernanda Vi\u00e9gas Oriol Vinyals Pete Warden Martin Wattenberg Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. https:\/\/www.tensorflow.org\/ Software available from tensorflow.org."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2012.325"},{"key":"e_1_3_2_2_5_1","volume-title":"Non-Smooth Newton Methods for Deformable Multi-Body Dynamics. In submission","year":"2018"},{"key":"e_1_3_2_2_6_1","volume-title":"Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control. International Conference on Learning Representations","author":"Berseth Glen","year":"2018"},{"key":"e_1_3_2_2_7_1","volume-title":"Cooper and Dana Ballard","author":"Joseph","year":"2012"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1618452.1618516"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1781156"},{"key":"e_1_3_2_2_10_1","unstructured":"Taku Komura Daniel Holden Jun Saito. {n. d.}. Motion capture database. http:\/\/theorangeduck.com\/media\/uploads\/other_stuff\/motionsynth_code.zip.  Taku Komura Daniel Holden Jun Saito. {n. d.}. Motion capture database. http:\/\/theorangeduck.com\/media\/uploads\/other_stuff\/motionsynth_code.zip."},{"key":"e_1_3_2_2_11_1","unstructured":"Prafulla Dhariwal Christopher Hesse Oleg Klimov Alex Nichol Matthias Plappert Alec Radford John Schulman Szymon Sidor and Yuhuai Wu. 2017. OpenAI Baselines. https:\/\/github.com\/openai\/baselines.  Prafulla Dhariwal Christopher Hesse Oleg Klimov Alex Nichol Matthias Plappert Alec Radford John Schulman Szymon Sidor and Yuhuai Wu. 2017. OpenAI Baselines. https:\/\/github.com\/openai\/baselines."},{"key":"e_1_3_2_2_12_1","volume-title":"Motion in Games","author":"Feng Andrew"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2012.03189.x"},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the ACM SIGGRAPH\/Eurographics Symposium on Computer Animation (SCA '12)","author":"Geijtenbeek T."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508399"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/218380.218411"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Nikolaus Hansen. 2007. The CMA Evolution Strategy: A Comparing Review. 75--102 pages.  Nikolaus Hansen. 2007. The CMA Evolution Strategy: A Comparing Review. 75--102 pages.","DOI":"10.1007\/3-540-32494-1_4"},{"key":"e_1_3_2_2_18_1","volume-title":"Emergence of Locomotion Behaviours in Rich Environments. CoRR abs\/1707.02286","author":"Heess Nicolas","year":"2017"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/218380.218414"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073663"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925975"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-016-1338-5"},{"key":"e_1_3_2_2_23_1","volume-title":"Self-Normalizing Neural Networks. CoRR abs\/1706.02515","author":"Klambauer G\u00fcnter","year":"2017"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566605"},{"key":"e_1_3_2_2_25_1","unstructured":"Vikash Kumar. {n. d.}. Humanoid 1.31. http:\/\/www.mujoco.org\/forum\/index.php?resources\/humanoid.5\/.  Vikash Kumar. {n. d.}. Humanoid 1.31. http:\/\/www.mujoco.org\/forum\/index.php?resources\/humanoid.5\/."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/1921427.1921447"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237231"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1781155"},{"key":"e_1_3_2_2_29_1","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems -","volume":"1","author":"Levine Sergey","year":"2014"},{"key":"e_1_3_2_2_30_1","volume-title":"Learning Complex Neural Network Policies with Trajectory Optimization. In ICML '14: Proceedings of the 31st International Conference on Machine Learning.","author":"Levine Sergey","year":"2014"},{"key":"e_1_3_2_2_31_1","volume-title":"Continuous control with deep reinforcement learning. CoRR abs\/1509.02971","author":"Lillicrap Timothy P.","year":"2015"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2893476"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12571"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778865"},{"key":"e_1_3_2_2_35_1","volume-title":"Learning human behaviors from motion capture by adversarial imitation. CoRR abs\/1707.02201","author":"Merel Josh","year":"2017"},{"key":"e_1_3_2_2_36_1","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems -","volume":"2","author":"Mordatch Igor","year":"2015"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Igor Mordatch and Emanuel Todorov. 2014. Combining the benefts of function approximation and trajectory optimization. In In Robotics: Science and Systems (RSS.  Igor Mordatch and Emanuel Todorov. 2014. Combining the benefts of function approximation and trajectory optimization. In In Robotics: Science and Systems (RSS.","DOI":"10.15607\/RSS.2014.X.052"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508365"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766910"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925881"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3099564.3099567"},{"key":"e_1_3_2_2_44_1","volume-title":"Trust Region Policy Optimization. CoRR abs\/1502.05477","author":"Schulman John","year":"2015"},{"key":"e_1_3_2_2_45_1","volume-title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation. CoRR abs\/1506.02438","author":"Schulman John","year":"2015"},{"key":"e_1_3_2_2_46_1","volume-title":"Proximal Policy Optimization Algorithms. CoRR abs\/1707.06347","author":"Schulman John","year":"2017"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/192161.192167"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276511"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964953"},{"key":"e_1_3_2_2_50_1","volume-title":"Reinforcement Learning in Continuous Action Spaces. In 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning. 272--279","author":"van Hasselt H."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185521"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/1661412.1618514"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/1833349.1778810"},{"key":"e_1_3_2_2_54_1","volume-title":"2014 International Conference on Audio, Language and Image Processing. 780--785","author":"Wang Y."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276509"}],"event":{"name":"MIG '18: Motion, Interaction and Games","location":"Limassol Cyprus","acronym":"MIG '18","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the 11th Annual International Conference on Motion, Interaction, and Games"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3274247.3274506","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3274247.3274506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:44:05Z","timestamp":1750207445000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3274247.3274506"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,8]]},"references-count":55,"alternative-id":["10.1145\/3274247.3274506","10.1145\/3274247"],"URL":"https:\/\/doi.org\/10.1145\/3274247.3274506","relation":{},"subject":[],"published":{"date-parts":[[2018,11,8]]}}}