Zobrazeno 1 - 10
of 82
pro vyhledávání: '"Pan, Yunpeng"'
Many neural networks use the tanh activation function, however when given a probability distribution as input, the problem of computing the output distribution in neural networks with tanh activation has not yet been addressed. One important example
Externí odkaz:
http://arxiv.org/abs/1806.09431
Autor:
Ren, Kailiang, Miao, Jiajia, Shen, Wenzhuo, Su, Huanhuan, Pan, Yunpeng, Zhao, Jiajin, Pan, Xiangyu, Li, Yuan, Fu, Yaokun, Zhang, Lu, Han, Shumin
Publikováno v:
In Progress in Natural Science: Materials International December 2022 32(6):684-692
Autor:
Pan, Yunpeng, Tian, Lei, Wang, Wenfeng, Zhao, Jiajin, Li, Yuan, Xi, Ning, Jian, Lu, Han, Shumin, Zhang, Lu
Publikováno v:
In Electrochimica Acta 20 October 2022 430
Autor:
Pan, Yunpeng, Cheng, Ching-An, Saigol, Kamil, Lee, Keuntaek, Yan, Xinyan, Theodorou, Evangelos, Boots, Byron
We present an end-to-end imitation learning system for agile, off-road autonomous driving using only low-cost sensors. By imitating a model predictive controller equipped with advanced sensors, we train a deep neural network control policy to map raw
Externí odkaz:
http://arxiv.org/abs/1709.07174
In this paper we develop a novel, discrete-time optimal control framework for mechanical systems with uncertain model parameters. We consider finite-horizon problems where the performance index depends on the statistical moments of the stochastic sys
Externí odkaz:
http://arxiv.org/abs/1705.05506
Trajectory optimization of a controlled dynamical system is an essential part of autonomy, however many trajectory optimization techniques are limited by the fidelity of the underlying parametric model. In the field of robotics, a lack of model knowl
Externí odkaz:
http://arxiv.org/abs/1702.04800
Robotic systems must be able to quickly and robustly make decisions when operating in uncertain and dynamic environments. While Reinforcement Learning (RL) can be used to compute optimal policies with little prior knowledge about the environment, it
Externí odkaz:
http://arxiv.org/abs/1608.06235
Many machine learning tasks, such as learning with invariance and policy evaluation in reinforcement learning, can be characterized as problems of learning from conditional distributions. In such problems, each sample $x$ itself is associated with a
Externí odkaz:
http://arxiv.org/abs/1607.04579
We present a data-driven optimal control framework that can be viewed as a generalization of the path integral (PI) control approach. We find iterative feedback control laws without parameterization based on probabilistic representation of learned dy
Externí odkaz:
http://arxiv.org/abs/1509.01846
Over the last few years, sampling-based stochastic optimal control (SOC) frameworks have shown impressive performances in reinforcement learning (RL) with applications in robotics. However, such approaches require a large amount of samples from many
Externí odkaz:
http://arxiv.org/abs/1412.3038