Picture for Xiaoming Duan

Xiaoming Duan

Shanghai Jiaotong University

Analysis of On-policy Policy Gradient Methods under the Distribution Mismatch

Add code
Mar 28, 2025
Viaarxiv icon

Stochastic Trajectory Optimization for Demonstration Imitation

Add code
Aug 07, 2024
Figure 1 for Stochastic Trajectory Optimization for Demonstration Imitation
Figure 2 for Stochastic Trajectory Optimization for Demonstration Imitation
Figure 3 for Stochastic Trajectory Optimization for Demonstration Imitation
Viaarxiv icon

Inverse Reinforcement Learning with Unknown Reward Model based on Structural Risk Minimization

Add code
Dec 27, 2023
Viaarxiv icon

Multiplayer Homicidal Chauffeur Reach-Avoid Games: A Pursuit Enclosure Function Approach

Add code
Nov 04, 2023
Viaarxiv icon

HiCRISP: A Hierarchical Closed-Loop Robotic Intelligent Self-Correction Planner

Add code
Sep 21, 2023
Figure 1 for HiCRISP: A Hierarchical Closed-Loop Robotic Intelligent Self-Correction Planner
Figure 2 for HiCRISP: A Hierarchical Closed-Loop Robotic Intelligent Self-Correction Planner
Figure 3 for HiCRISP: A Hierarchical Closed-Loop Robotic Intelligent Self-Correction Planner
Figure 4 for HiCRISP: A Hierarchical Closed-Loop Robotic Intelligent Self-Correction Planner
Viaarxiv icon

Affordance-Driven Next-Best-View Planning for Robotic Grasping

Add code
Sep 18, 2023
Viaarxiv icon

Control Input Inference of Mobile Agents under Unknown Objective

Add code
Jul 20, 2023
Viaarxiv icon

Reinforcement Learning with Temporal-Logic-Based Causal Diagrams

Add code
Jun 23, 2023
Viaarxiv icon

Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning

Add code
Jan 20, 2023
Viaarxiv icon

Adaptive Obstacle Avoidance Algorithm Based on Trajectory Learning

Add code
Jun 07, 2022
Figure 1 for Adaptive Obstacle Avoidance Algorithm Based on Trajectory Learning
Figure 2 for Adaptive Obstacle Avoidance Algorithm Based on Trajectory Learning
Figure 3 for Adaptive Obstacle Avoidance Algorithm Based on Trajectory Learning
Figure 4 for Adaptive Obstacle Avoidance Algorithm Based on Trajectory Learning
Viaarxiv icon