{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:55:10Z","timestamp":1729637710910,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"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":[[2021,10,17]]},"DOI":"10.1109\/smc52423.2021.9658875","type":"proceedings-article","created":{"date-parts":[[2022,1,6]],"date-time":"2022-01-06T20:34:35Z","timestamp":1641501275000},"page":"327-332","source":"Crossref","is-referenced-by-count":0,"title":["A Model-Based Method for Learning Locomotion Skills from Demonstration"],"prefix":"10.1109","author":[{"given":"Hyunseong","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sukmin","family":"Yoon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong-Duk","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref33"},{"journal-title":"Spectral Norm Regularization for Improving the Generalizability of Deep Learning","year":"2017","author":"yoshida","key":"ref32"},{"journal-title":"Regularisation of neural networks by enforcing lipschitz continuity","year":"2020","author":"gouk","key":"ref31"},{"journal-title":"Training robust neural networks using Lipschitz bounds","year":"2020","author":"pauli","key":"ref30"},{"key":"ref10","article-title":"Improved Training of Wasserstein GANs","author":"gulrajani","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref11","article-title":"Sample Efficient Imitation Learning for Continuous Control","author":"sasaki","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref12","article-title":"Trust Region Policy Optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref13","article-title":"Maximum Entropy Inverse Reinforcement Learning","author":"ziebart","year":"2008","journal-title":"Int Conference on Artificial Intelligence (AAAI)"},{"key":"ref14","article-title":"Modeling Interaction via the Principle of Maximum Causal Entropy","author":"ziebart","year":"2010","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref15","article-title":"Addressing Function Approximation Error in Actor-Critic Methods","author":"fujimoto","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref16","article-title":"Sample-Efficient Imitation Learning via Generative Adversarial Nets","author":"blond","year":"1618","journal-title":"International Conference on Artificial Intelligence and Statistics (AISTATS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref18","article-title":"Exploration by random network distillation","author":"burda","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref19","article-title":"PILCO: A Model-Based and Data-Efficient Approach to Policy Search","author":"deisenroth","year":"2011","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref28","first-page":"19291958","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","article-title":"Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning","author":"kostrikov","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1944345.1944349"},{"key":"ref3","article-title":"End-to-End Differentiable Adversarial Imitation Learning","author":"baram","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref6","article-title":"Improving Generalization and Stability of Generative Adversarial Networks","author":"thanh-tung","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"529533","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref5","article-title":"Imitation Learning via Off-Policy Distribution Matching","author":"kostrikov","year":"2020","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref8","article-title":"On Computation and Generalization of Generative Adversarial Imitation Learning","author":"chen","year":"2020","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref7","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"journal-title":"PyBullet Gymperium","year":"2018","author":"ellenberger","key":"ref2"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9590","article-title":"Improving Multi-Step Prediction of Learned Time Series Models","author":"venkatraman","year":"2015","journal-title":"Int Conference on Artificial Intelligence (AAAI)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914406"},{"key":"ref20","article-title":"Lipschitz Continuity in Modelbased Reinforcement Learning","author":"asadi","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref22","article-title":"Generative Adversarial Imitation Learning","author":"ho","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref21","article-title":"Imagination-Augmented Agents for Deep Reinforcement Learning","author":"racani\u00e8re","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref24","article-title":"Learning Continuous Control Policies by Stochastic Value Gradients","author":"heess","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref23","article-title":"Generative Adversarial Nets, in Advances","author":"goodfellow","year":"2014","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_35"},{"key":"ref25","article-title":"A Simple Weight Decay Can Improve Generalization","author":"krogh","year":"1992","journal-title":"Advances in Neural IInformation Processing Systems"}],"event":{"name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2021,10,17]]},"location":"Melbourne, Australia","end":{"date-parts":[[2021,10,20]]}},"container-title":["2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9658572\/9658575\/09658875.pdf?arnumber=9658875","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T05:14:58Z","timestamp":1674364498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9658875\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/smc52423.2021.9658875","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]}}}