20 citations · 57 across the 8 of their papers we have counts for
9 papers
Propagating Uncertainty through the tanh Function with Application to Reservoir Computing
Manan Gandhi, Keuntaek Lee, Yunpeng Pan +1
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 w…
Agile Autonomous Driving using End-to-End Deep Imitation Learning
Yunpeng Pan, Ching-An Cheng, Kamil Saigol +4
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 adva…
Stochastic trajectory optimization for mechanical systems with parametric uncertainties
George I. Boutselis, Yunpeng Pan, Gerardo De La Tore +1
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 perf…
Pseudospectral Model Predictive Control under Partially Learned Dynamics
Manan Gandhi, Yunpeng Pan, Evangelos Theodorou
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 underl…
Adaptive Probabilistic Trajectory Optimization via Efficient Approximate Inference
Yunpeng Pan, Xinyan Yan, Evangelos Theodorou +1
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 o…
Learning from Conditional Distributions via Dual Embeddings
Bo Dai, Niao He, Yunpeng Pan +2
Many machine learning tasks, such as learning with invariance and policy evaluation in reinforcement learning, can be characterized as problems of learning from conditional distrib…
Sample Efficient Path Integral Control under Uncertainty
Yunpeng Pan, Evangelos A. Theodorou, Michail Kontitsis
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 withou…
Model-based Path Integral Stochastic Control: A Bayesian Nonparametric Approach
Yunpeng Pan, Evangelos A. Theodorou, Michail Kontitsis
Over the last few years, sampling-based stochastic optimal control (SOC) frameworks have shown impressive performances in reinforcement learning (RL) with applications in robotics.…
Nonparametric Infinite Horizon Kullback-Leibler Stochastic Control
Yunpeng Pan, Evangelos Theodorou
We present two nonparametric approaches to Kullback-Leibler (KL) control, or linearly-solvable Markov decision problem (LMDP) based on Gaussian processes (GP) and Nyström approxima…