Picture for Xinyan Yan

Xinyan Yan

Explaining Fast Improvement in Online Policy Optimization

Add code
Jul 08, 2020
Figure 1 for Explaining Fast Improvement in Online Policy Optimization
Figure 2 for Explaining Fast Improvement in Online Policy Optimization
Figure 3 for Explaining Fast Improvement in Online Policy Optimization
Viaarxiv icon

Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods

Add code
Aug 08, 2019
Figure 1 for Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods
Figure 2 for Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods
Figure 3 for Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods
Figure 4 for Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods
Viaarxiv icon

Continuous-Time Gaussian Process Motion Planning via Probabilistic Inference

Add code
Nov 22, 2018
Figure 1 for Continuous-Time Gaussian Process Motion Planning via Probabilistic Inference
Figure 2 for Continuous-Time Gaussian Process Motion Planning via Probabilistic Inference
Figure 3 for Continuous-Time Gaussian Process Motion Planning via Probabilistic Inference
Figure 4 for Continuous-Time Gaussian Process Motion Planning via Probabilistic Inference
Viaarxiv icon

Predictor-Corrector Policy Optimization

Add code
Oct 15, 2018
Figure 1 for Predictor-Corrector Policy Optimization
Figure 2 for Predictor-Corrector Policy Optimization
Figure 3 for Predictor-Corrector Policy Optimization
Viaarxiv icon

Accelerating Imitation Learning with Predictive Models

Add code
Oct 13, 2018
Figure 1 for Accelerating Imitation Learning with Predictive Models
Figure 2 for Accelerating Imitation Learning with Predictive Models
Viaarxiv icon

Agile Off-Road Autonomous Driving Using End-to-End Deep Imitation Learning

Add code
Sep 10, 2018
Figure 1 for Agile Off-Road Autonomous Driving Using End-to-End Deep Imitation Learning
Figure 2 for Agile Off-Road Autonomous Driving Using End-to-End Deep Imitation Learning
Figure 3 for Agile Off-Road Autonomous Driving Using End-to-End Deep Imitation Learning
Figure 4 for Agile Off-Road Autonomous Driving Using End-to-End Deep Imitation Learning
Viaarxiv icon

Fast Policy Learning through Imitation and Reinforcement

Add code
May 26, 2018
Figure 1 for Fast Policy Learning through Imitation and Reinforcement
Viaarxiv icon

Manifold Regularization for Kernelized LSTD

Add code
Oct 15, 2017
Viaarxiv icon

Approximately Optimal Continuous-Time Motion Planning and Control via Probabilistic Inference

Add code
Feb 27, 2017
Figure 1 for Approximately Optimal Continuous-Time Motion Planning and Control via Probabilistic Inference
Figure 2 for Approximately Optimal Continuous-Time Motion Planning and Control via Probabilistic Inference
Figure 3 for Approximately Optimal Continuous-Time Motion Planning and Control via Probabilistic Inference
Figure 4 for Approximately Optimal Continuous-Time Motion Planning and Control via Probabilistic Inference
Viaarxiv icon

Adaptive Probabilistic Trajectory Optimization via Efficient Approximate Inference

Add code
Sep 11, 2016
Figure 1 for Adaptive Probabilistic Trajectory Optimization via Efficient Approximate Inference
Figure 2 for Adaptive Probabilistic Trajectory Optimization via Efficient Approximate Inference
Figure 3 for Adaptive Probabilistic Trajectory Optimization via Efficient Approximate Inference
Viaarxiv icon