Picture for Shengbo Eben Li

Shengbo Eben Li

Robust Safe Reinforcement Learning under Adversarial Disturbances

Add code
Oct 11, 2023
Figure 1 for Robust Safe Reinforcement Learning under Adversarial Disturbances
Figure 2 for Robust Safe Reinforcement Learning under Adversarial Disturbances
Figure 3 for Robust Safe Reinforcement Learning under Adversarial Disturbances
Figure 4 for Robust Safe Reinforcement Learning under Adversarial Disturbances
Viaarxiv icon

Bridging the Gap between Newton-Raphson Method and Regularized Policy Iteration

Add code
Oct 11, 2023
Figure 1 for Bridging the Gap between Newton-Raphson Method and Regularized Policy Iteration
Figure 2 for Bridging the Gap between Newton-Raphson Method and Regularized Policy Iteration
Viaarxiv icon

SEPT: Towards Efficient Scene Representation Learning for Motion Prediction

Add code
Oct 03, 2023
Viaarxiv icon

Safe Reinforcement Learning with Dual Robustness

Add code
Sep 13, 2023
Figure 1 for Safe Reinforcement Learning with Dual Robustness
Figure 2 for Safe Reinforcement Learning with Dual Robustness
Viaarxiv icon

Feasible Policy Iteration

Add code
Apr 18, 2023
Viaarxiv icon

Smoothing Policy Iteration for Zero-sum Markov Games

Add code
Dec 03, 2022
Figure 1 for Smoothing Policy Iteration for Zero-sum Markov Games
Figure 2 for Smoothing Policy Iteration for Zero-sum Markov Games
Figure 3 for Smoothing Policy Iteration for Zero-sum Markov Games
Figure 4 for Smoothing Policy Iteration for Zero-sum Markov Games
Viaarxiv icon

Integrated Decision and Control for High-Level Automated Vehicles by Mixed Policy Gradient and Its Experiment Verification

Add code
Oct 19, 2022
Figure 1 for Integrated Decision and Control for High-Level Automated Vehicles by Mixed Policy Gradient and Its Experiment Verification
Figure 2 for Integrated Decision and Control for High-Level Automated Vehicles by Mixed Policy Gradient and Its Experiment Verification
Figure 3 for Integrated Decision and Control for High-Level Automated Vehicles by Mixed Policy Gradient and Its Experiment Verification
Figure 4 for Integrated Decision and Control for High-Level Automated Vehicles by Mixed Policy Gradient and Its Experiment Verification
Viaarxiv icon

Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate

Add code
Oct 14, 2022
Figure 1 for Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate
Figure 2 for Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate
Figure 3 for Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate
Figure 4 for Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate
Viaarxiv icon

Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model

Add code
Oct 08, 2022
Figure 1 for Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model
Figure 2 for Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model
Figure 3 for Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model
Figure 4 for Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model
Viaarxiv icon

Synthesize Efficient Safety Certificates for Learning-Based Safe Control using Magnitude Regularization

Add code
Sep 23, 2022
Figure 1 for Synthesize Efficient Safety Certificates for Learning-Based Safe Control using Magnitude Regularization
Figure 2 for Synthesize Efficient Safety Certificates for Learning-Based Safe Control using Magnitude Regularization
Figure 3 for Synthesize Efficient Safety Certificates for Learning-Based Safe Control using Magnitude Regularization
Figure 4 for Synthesize Efficient Safety Certificates for Learning-Based Safe Control using Magnitude Regularization
Viaarxiv icon