Picture for Wenjie Shi

Wenjie Shi

Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning

Add code
Sep 04, 2023
Viaarxiv icon

Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning

Add code
Dec 06, 2021
Figure 1 for Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning
Figure 2 for Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning
Figure 3 for Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning
Figure 4 for Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning
Viaarxiv icon

Self-Supervised Discovering of Causal Features: Towards Interpretable Reinforcement Learning

Add code
Mar 21, 2020
Figure 1 for Self-Supervised Discovering of Causal Features: Towards Interpretable Reinforcement Learning
Figure 2 for Self-Supervised Discovering of Causal Features: Towards Interpretable Reinforcement Learning
Figure 3 for Self-Supervised Discovering of Causal Features: Towards Interpretable Reinforcement Learning
Figure 4 for Self-Supervised Discovering of Causal Features: Towards Interpretable Reinforcement Learning
Viaarxiv icon

Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning

Add code
Sep 07, 2019
Figure 1 for Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning
Figure 2 for Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning
Figure 3 for Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning
Figure 4 for Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning
Viaarxiv icon

Multi Pseudo Q-learning Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehicles

Add code
Sep 07, 2019
Figure 1 for Multi Pseudo Q-learning Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehicles
Figure 2 for Multi Pseudo Q-learning Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehicles
Figure 3 for Multi Pseudo Q-learning Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehicles
Figure 4 for Multi Pseudo Q-learning Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehicles
Viaarxiv icon

Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning

Add code
Sep 07, 2019
Figure 1 for Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning
Figure 2 for Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning
Viaarxiv icon