Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Su, Hao"'
Autor:
Liu, Shuang, Su, Hao
We propose and analyze a kernelized version of Q-learning. Although a kernel space is typically infinite-dimensional, extensive study has shown that generalization is only affected by the effective dimension of the data. We incorporate such ideas int
Externí odkaz:
http://arxiv.org/abs/2204.10349
Autor:
Liu, Shuang, Su, Hao
Reinforcement learning (RL) has traditionally been understood from an episodic perspective; the concept of non-episodic RL, where there is no restart and therefore no reliable recovery, remains elusive. A fundamental question in non-episodic RL is ho
Externí odkaz:
http://arxiv.org/abs/2002.05138
Consider an imitation learning problem that the imitator and the expert have different dynamics models. Most of the current imitation learning methods fail because they focus on imitating actions. We propose a novel state alignment-based imitation le
Externí odkaz:
http://arxiv.org/abs/1911.10947
Autor:
Jia, Zhiwei, Su, Hao
Recent advances in deep learning theory have evoked the study of generalizability across different local minima of deep neural networks (DNNs). While current work focused on either discovering properties of good local minima or developing regularizat
Externí odkaz:
http://arxiv.org/abs/1911.08192
Model-based reinforcement learning (MBRL) aims to learn a dynamic model to reduce the number of interactions with real-world environments. However, due to estimation error, rollouts in the learned model, especially those of long horizons, fail to mat
Externí odkaz:
http://arxiv.org/abs/1909.11821
Autor:
Li, Jiachen, Vuong, Quan, Liu, Shuang, Liu, Minghua, Ciosek, Kamil, Ross, Keith, Christensen, Henrik Iskov, Su, Hao
We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks sampled from the same distribution. The task identities of the unseen
Externí odkaz:
http://arxiv.org/abs/1909.11373
The importance of training robust neural network grows as 3D data is increasingly utilized in deep learning for vision tasks in robotics, drone control, and autonomous driving. One commonly used 3D data type is 3D point clouds, which describe shape i
Externí odkaz:
http://arxiv.org/abs/1908.06062
An agent that has well understood the environment should be able to apply its skills for any given goals, leading to the fundamental problem of learning the Universal Value Function Approximator (UVFA). A UVFA learns to predict the cumulative rewards
Externí odkaz:
http://arxiv.org/abs/1908.05451
Recently, reinforcement learning (RL) algorithms have demonstrated remarkable success in learning complicated behaviors from minimally processed input. However, most of this success is limited to simulation. While there are promising successes in app
Externí odkaz:
http://arxiv.org/abs/1903.11774
3D object classification and segmentation using deep neural networks has been extremely successful. As the problem of identifying 3D objects has many safety-critical applications, the neural networks have to be robust against adversarial changes to t
Externí odkaz:
http://arxiv.org/abs/1901.03006