One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks, Tuomas Haarnoja, Aurick Zhou, Kristian Hartikainen, George Tucker, Sehoon Ha, Jie Tan, Vikash Kumar, Henry Zhu, Abhishek Gupta, Pieter Abbeel, Sergey Levine. Soft Actor-Critic Algorithms and Applications, Himanshu Sahni, Toby Buckley, Pieter Abbeel, Ilya Kuzovkin. Joshua Achiam, Ethan Knight, Pieter Abbeel. Towards Characterizing Divergence in Deep Q-Learning, Russell Mendonca, Abhishek Gupta, Rosen Kralev, Pieter Abbeel, Sergey Levine, Chelsea Finn. Hellerstein, Sanjay Krishnan, Ion Stoica. Zongheng Yang, Eric Liang, Amog Kamsetty, Chenggang Wu, Yan Duan, Xi Chen, Pieter Abbeel, Joseph M. Selectivity Estimation with Deep Likelihood Models, ![]() Xue Bin (Jason) Peng, Michael Chang, Grace Zhang, Pieter Abbeel, Sergey Levine.Ĭompression with Flows via Local Bits-Back Coding, MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies, Giulia Vezzani, Abhishek Gupta, Lorenzo Natale, Pieter Abbeel. Learning latent state representation for speeding up exploration, Yiming Ding, Carlos Florensa, Mariano Phielipp, Pieter Abbeel. Li, Carlos Florensa, Ignasi Clavera, Pieter Abbeel. Sub-policy Adaptation for Hierarchical Reinforcement Learning,Īlexander C. Roshan Rao, Nicholas Bhattacharya, Neil Thomas, Yan Duan, Xi Chen, John Canny, Pieter Abbeel, Yun S. Lee, Anusha Nagabandi, Pieter Abbeel, Sergey Levine.Įvaluating Protein Transfer Learning with TAPE, Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model,Īlex X. Tingwu Wang, Xuchan Bao, Ignasi Clavera, Jerrick Hoang, Yeming Wen, Eric Langlois, Shunshi Zhang, Guodong Zhang, Pieter Abbeel, Jimmy Ba. A prime example is the BLUE project, where we study how advances in AI might completely change the robot design paradigm.īenchmarking Model-Based Reinforcement Learning, While our main pushes are around advancing AI to make existing systems more intelligent, we also investigate how AI advances might transform areas from the ground up. It's our general belief that if a science or engineering discipline heavily relies on human intuition acquired from seeing many scenarios then it is likely a great fit for AI to help out. We also like to investigate how AI could open up new opportunities in other disciplines. ![]() A lot of our research is driven by trying to build ever more intelligent systems, which has us pushing the frontiers of deep reinforcement learning, deep imitation learning, deep unsupervised learning, transfer learning, meta-learning, and learning to learn, as well as study the influence of AI on society.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |