{ "status": "ok", "message-type": "work", "message-version": "1.0.0", "message": { "indexed": { "date-parts": [ [ 2020, 4, 4 ] ], "date-time": "2020-04-04T01:11:55Z", "timestamp": 1585962715213 }, "reference-count": 55, "publisher": "Association for Computing Machinery (ACM)", "issue": "4", "license": [ { "URL": "http://www.acm.org/publications/policies/copyright_policy#Background", "start": { "date-parts": [ [ 2018, 7, 30 ] ], "date-time": "2018-07-30T00:00:00Z", "timestamp": 1532908800000 }, "delay-in-days": 0, "content-version": "vor" } ], "funder": [ { "DOI": "10.13039/501100000038", "name": "Natural Sciences and Engineering Research Council of Canada", "doi-asserted-by": "crossref", "award": [] }, { "name": "Berkeley", "award": [] } ], "content-domain": { "domain": [], "crossmark-restriction": false }, "short-container-title": [ "ACM Trans. Graph." ], "published-print": { "date-parts": [ [ 2018, 8, 10 ] ] }, "DOI": "10.1145/3197517.3201311", "type": "journal-article", "created": { "date-parts": [ [ 2018, 7, 31 ] ], "date-time": "2018-07-31T15:56:23Z", "timestamp": 1533052583000 }, "page": "1-14", "source": "Crossref", "is-referenced-by-count": 48, "title": [ "DeepMimic" ], "prefix": "10.1145", "volume": "37", "author": [ { "given": "Xue Bin", "family": "Peng", "sequence": "first", "affiliation": [ { "name": "University of California" } ] }, { "given": "Pieter", "family": "Abbeel", "sequence": "additional", "affiliation": [ { "name": "University of California" } ] }, { "given": "Sergey", "family": "Levine", "sequence": "additional", "affiliation": [ { "name": "University of California" } ] }, { "given": "Michiel", "family": "van de Panne", "sequence": "additional", "affiliation": [ { "name": "University of British Columbia" } ] } ], "member": "320", "reference": [ { "key": "e_1_2_2_1_1", "DOI": "10.1145/2485895.2485907", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_2_1", "DOI": "10.1145/2897824.2925893", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_3_1", "unstructured": "Marc G. Bellemare Sriram Srinivasan Georg Ostrovski Tom Schaul David Saxton and R\u00e9mi Munos. 2016. Unifying Count-Based Exploration and Intrinsic Motivation. CoRR abs/1606.01868 (2016). arXiv:1606.01868 Marc G. Bellemare Sriram Srinivasan Georg Ostrovski Tom Schaul David Saxton and R\u00e9mi Munos. 2016. Unifying Count-Based Exploration and Intrinsic Motivation. CoRR abs/1606.01868 (2016). arXiv:1606.01868" }, { "key": "e_1_2_2_4_1", "unstructured": "Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016a. OpenAI Gym. CoRR abs/1606.01540 (2016). arXiv:1606.01540 Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016a. OpenAI Gym. CoRR abs/1606.01540 (2016). arXiv:1606.01540" }, { "key": "e_1_2_2_5_1", "unstructured": "Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016b. OpenAI Gym. arXiv:arXiv:1606.01540 Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016b. OpenAI Gym. arXiv:arXiv:1606.01540" }, { "key": "e_1_2_2_6_1", "unstructured": "Bullet. 2015. Bullet Physics Library http://bulletphysics.org. Bullet. 2015. Bullet Physics Library http://bulletphysics.org." }, { "key": "e_1_2_2_7_1", "DOI": "10.1145/1618452.1618516", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_8_1", "unstructured": "Stelian Coros Philippe Beaudoin and Michiel van de Panne. 2010. Generalized Biped Walking Control. ACM Transctions on Graphics 29 4 (2010) Article 130. 10.1145/1778765.1781156 Stelian Coros Philippe Beaudoin and Michiel van de Panne. 2010. Generalized Biped Walking Control. ACM Transctions on Graphics 29 4 (2010) Article 130. 10.1145/1778765.1781156" }, { "key": "e_1_2_2_9_1", "unstructured": "M. Da Silva Y. Abe and J. Popovic. 2008. Simulation of Human Motion Data using Short-Horizon Model-Predictive Control. Computer Graphics Forum (2008). M. Da Silva Y. Abe and J. Popovic. 2008. Simulation of Human Motion Data using Short-Horizon Model-Predictive Control. Computer Graphics Forum (2008)." }, { "key": "e_1_2_2_10_1", "unstructured": "Yan Duan Xi Chen Rein Houthooft John Schulman and Pieter Abbeel. 2016. Benchmarking Deep Reinforcement Learning for Continuous Control. CoRR abs/1604.06778 (2016). arXiv:1604.06778 Yan Duan Xi Chen Rein Houthooft John Schulman and Pieter Abbeel. 2016. Benchmarking Deep Reinforcement Learning for Continuous Control. CoRR abs/1604.06778 (2016). arXiv:1604.06778" }, { "key": "e_1_2_2_11_1", "author": "Fu Justin", "volume-title": "Advances in Neural Information Processing Systems 30. Curran Associates" }, { "key": "e_1_2_2_12_1", "DOI": "10.1145/2682626", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_13_1", "DOI": "10.1145/2767002", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_14_1", "unstructured": "Nicolas Heess Dhruva TB Srinivasan Sriram Jay Lemmon Josh Merel Greg Wayne Yuval Tassa Tom Erez Ziyu Wang S. M. Ali Eslami Martin A. Riedmiller and David Silver. 2017. Emergence of Locomotion Behaviours in Rich Environments. CoRR abs/1707.02286 (2017). arXiv:1707.02286 Nicolas Heess Dhruva TB Srinivasan Sriram Jay Lemmon Josh Merel Greg Wayne Yuval Tassa Tom Erez Ziyu Wang S. M. Ali Eslami Martin A. Riedmiller and David Silver. 2017. Emergence of Locomotion Behaviours in Rich Environments. CoRR abs/1707.02286 (2017). arXiv:1707.02286" }, { "key": "e_1_2_2_15_1", "unstructured": "Nicolas Heess Gregory Wayne Yuval Tassa Timothy P. Lillicrap Martin A. Riedmiller and David Silver. 2016. Learning and Transfer of Modulated Locomotor Controllers. CoRR abs/1610.05182 (2016). arXiv:1610.05182 Nicolas Heess Gregory Wayne Yuval Tassa Timothy P. Lillicrap Martin A. Riedmiller and David Silver. 2016. Learning and Transfer of Modulated Locomotor Controllers. CoRR abs/1610.05182 (2016). arXiv:1610.05182" }, { "key": "e_1_2_2_16_1", "author": "Ho Jonathan", "volume-title": "Advances in Neural Information Processing Systems 29. Curran Associates" }, { "key": "e_1_2_2_17_1", "DOI": "10.1145/3072959.3073663", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_18_1", "DOI": "10.1145/2897824.2925975", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_19_1", "unstructured": "Rein Houthooft Xi Chen Yan Duan John Schulman Filip De Turck and Pieter Abbeel. 2016. Curiosity-driven Exploration in Deep Reinforcement Learning via Bayesian Neural Networks. CoRR abs/1605.09674 (2016). arXiv:1605.09674 Rein Houthooft Xi Chen Yan Duan John Schulman Filip De Turck and Pieter Abbeel. 2016. Curiosity-driven Exploration in Deep Reinforcement Learning via Bayesian Neural Networks. CoRR abs/1605.09674 (2016). arXiv:1605.09674" }, { "key": "e_1_2_2_20_1", "DOI": "10.1145/1833349.1781155", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_21_1", "DOI": "10.1145/2661229.2661233", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_22_1", "DOI": "10.1145/1866158.1866160", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_23_1", "DOI": "10.1145/2185520.2185524", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_24_1", "DOI": "10.1145/3083723", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_25_1", "DOI": "10.1145/2893476", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_26_1", "unstructured": "Libin Liu KangKang Yin Michiel van de Panne Tianjia Shao and Weiwei Xu. 2010. Sampling-based Contact-rich Motion Control. ACM Transctions on Graphics 29 4 (2010) Article 128. 10.1145/1778765.1778865 Libin Liu KangKang Yin Michiel van de Panne Tianjia Shao and Weiwei Xu. 2010. Sampling-based Contact-rich Motion Control. ACM Transctions on Graphics 29 4 (2010) Article 128. 10.1145/1778765.1778865", "DOI": "10.1145/1833349.1778865", "doi-asserted-by": "crossref" }, { "key": "e_1_2_2_27_1", "unstructured": "Josh Merel Yuval Tassa Dhruva TB Sriram Srinivasan Jay Lemmon Ziyu Wang Greg Wayne and Nicolas Heess. 2017. Learning human behaviors from motion capture by adversarial imitation. CoRR abs/1707.02201 (2017). arXiv:1707.02201 Josh Merel Yuval Tassa Dhruva TB Sriram Srinivasan Jay Lemmon Ziyu Wang Greg Wayne and Nicolas Heess. 2017. Learning human behaviors from motion capture by adversarial imitation. CoRR abs/1707.02201 (2017). arXiv:1707.02201" }, { "key": "e_1_2_2_28_1", "DOI": "10.1038/nature14236", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_29_1", "DOI": "10.1145/2185520.2185539", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_30_1", "DOI": "10.1145/1531326.1531387", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_31_1", "unstructured": "Ashvin Nair Bob McGrew Marcin Andrychowicz Wojciech Zaremba and Pieter Abbeel. 2017. Overcoming Exploration in Reinforcement Learning with Demonstrations. CoRR abs/1709.10089 (2017). arXiv:1709.10089 Ashvin Nair Bob McGrew Marcin Andrychowicz Wojciech Zaremba and Pieter Abbeel. 2017. Overcoming Exploration in Reinforcement Learning with Demonstrations. CoRR abs/1709.10089 (2017). arXiv:1709.10089" }, { "key": "e_1_2_2_32_1", "DOI": "10.1145/2766910", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_33_1", "DOI": "10.1145/2897824.2925881", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_34_1", "DOI": "10.1145/3072959.3073602", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_35_1", "DOI": "10.1145/3099564.3099567", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_36_1", "unstructured": "Aravind Rajeswaran Sarvjeet Ghotra Sergey Levine and Balaraman Ravindran. 2016. EPOpt: Learning Robust Neural Network Policies Using Model Ensembles. CoRR abs/1610.01283 (2016). arXiv:1610.01283 Aravind Rajeswaran Sarvjeet Ghotra Sergey Levine and Balaraman Ravindran. 2016. EPOpt: Learning Robust Neural Network Policies Using Model Ensembles. CoRR abs/1610.01283 (2016). arXiv:1610.01283" }, { "key": "e_1_2_2_37_1", "unstructured": "Aravind Rajeswaran Vikash Kumar Abhishek Gupta John Schulman Emanuel Todorov and Sergey Levine. 2017. Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations. CoRR abs/1709.10087 (2017). arXiv:1709.10087 Aravind Rajeswaran Vikash Kumar Abhishek Gupta John Schulman Emanuel Todorov and Sergey Levine. 2017. Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations. CoRR abs/1709.10087 (2017). arXiv:1709.10087" }, { "key": "e_1_2_2_38_1", "DOI": "10.1145/1276377.1276510", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_39_1", "unstructured": "John Schulman Sergey Levine Philipp Moritz Michael I. Jordan and Pieter Abbeel. 2015a. Trust Region Policy Optimization. CoRR abs/1502.05477 (2015). arXiv:1502.05477 John Schulman Sergey Levine Philipp Moritz Michael I. Jordan and Pieter Abbeel. 2015a. Trust Region Policy Optimization. CoRR abs/1502.05477 (2015). arXiv:1502.05477" }, { "key": "e_1_2_2_40_1", "unstructured": "John Schulman Philipp Moritz Sergey Levine Michael I. Jordan and Pieter Abbeel. 2015b. High-Dimensional Continuous Control Using Generalized Advantage Estimation. CoRR abs/1506.02438 (2015). arXiv:1506.02438 John Schulman Philipp Moritz Sergey Levine Michael I. Jordan and Pieter Abbeel. 2015b. High-Dimensional Continuous Control Using Generalized Advantage Estimation. CoRR abs/1506.02438 (2015). arXiv:1506.02438" }, { "key": "e_1_2_2_41_1", "unstructured": "John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. CoRR abs/1707.06347 (2017). arXiv:1707.06347 John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. CoRR abs/1707.06347 (2017). arXiv:1707.06347" }, { "key": "e_1_2_2_42_1", "author": "Sharon Dana", "volume-title": "Proc. of IEEE International Conference on Robotics and Animation." }, { "key": "e_1_2_2_43_1", "DOI": "10.1145/1276377.1276511", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_44_1", "unstructured": "R. Sutton D. Mcallester S. Singh and Y. Mansour. 2001. Policy Gradient Methods for Reinforcement Learning with Function Approximation. 1057--1063 pages. R. Sutton D. Mcallester S. Singh and Y. Mansour. 2001. Policy Gradient Methods for Reinforcement Learning with Function Approximation. 1057--1063 pages." }, { "key": "e_1_2_2_45_1", "unstructured": "Richard S. Sutton and Andrew G. Barto. 1998. Introduction to Reinforcement Learning (1st ed.). MIT Press Cambridge MA USA. Richard S. Sutton and Andrew G. Barto. 1998. Introduction to Reinforcement Learning (1st ed.). MIT Press Cambridge MA USA." }, { "key": "e_1_2_2_46_1", "DOI": "10.1109/MCG.2011.30", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_47_1", "DOI": "10.1109/IROS.2012.6386025", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_48_1", "unstructured": "Yee Whye Teh Victor Bapst Wojciech Marian Czarnecki John Quan James Kirkpatrick Raia Hadsell Nicolas Heess and Razvan Pascanu. 2017. Distral: Robust Multitask Reinforcement Learning. CoRR abs/1707.04175 (2017). arXiv:1707.04175 Yee Whye Teh Victor Bapst Wojciech Marian Czarnecki John Quan James Kirkpatrick Raia Hadsell Nicolas Heess and Razvan Pascanu. 2017. Distral: Robust Multitask Reinforcement Learning. CoRR abs/1707.04175 (2017). arXiv:1707.04175" }, { "key": "e_1_2_2_49_1", "DOI": "10.1145/2601097.2601192", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_50_1", "unstructured": "Jack M. Wang Samuel R. Hamner Scott L. Delp Vladlen Koltun and More Specifically. 2012. Optimizing locomotion controllers using biologically-based actuators and objectives. ACM Trans. Graph (2012). 10.1145/2185520.2185521 Jack M. Wang Samuel R. Hamner Scott L. Delp Vladlen Koltun and More Specifically. 2012. Optimizing locomotion controllers using biologically-based actuators and objectives. ACM Trans. Graph (2012). 10.1145/2185520.2185521" }, { "key": "e_1_2_2_51_1", "unstructured": "Ronald J. Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning 8 3 (01 May 1992) 229--256. 10.1007/BF00992696 Ronald J. Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning 8 3 (01 May 1992) 229--256. 10.1007/BF00992696", "DOI": "10.1007/BF00992696", "doi-asserted-by": "crossref" }, { "key": "e_1_2_2_52_1", "DOI": "10.1145/3130800.3130833", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_53_1", "DOI": "10.1145/1778765.1778811", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_54_1", "DOI": "10.1111/j.1467-8659.2009.01625.x", "doi-asserted-by": "publisher" }, { "key": "e_1_2_2_55_1", "DOI": "10.1145/1276377.1276509", "doi-asserted-by": "publisher" } ], "container-title": [ "ACM Transactions on Graphics" ], "original-title": [], "language": "en", "link": [ { "URL": "http://dl.acm.org/ft_gateway.cfm?id=3201311&ftid=1991717&dwn=1", "content-type": "unspecified", "content-version": "vor", "intended-application": "similarity-checking" } ], "deposited": { "date-parts": [ [ 2020, 4, 4 ] ], "date-time": "2020-04-04T00:44:53Z", "timestamp": 1585961093000 }, "score": 1.0, "subtitle": [ "example-guided deep reinforcement learning of physics-based character skills" ], "short-title": [], "issued": { "date-parts": [ [ 2018, 8, 10 ] ] }, "references-count": 55, "journal-issue": { "published-print": { "date-parts": [ [ 2018, 8, 10 ] ] }, "issue": "4" }, "alternative-id": [ "10.1145/3197517.3201311" ], "URL": "http://dx.doi.org/10.1145/3197517.3201311", "relation": { "cites": [] }, "ISSN": [ "0730-0301", "1557-7368" ], "issn-type": [ { "value": "0730-0301", "type": "print" }, { "value": "1557-7368", "type": "electronic" } ] } }