Alert button
Picture for Jennie Si

Jennie Si

Alert button

Helen

Mitigating Estimation Errors by Twin TD-Regularized Actor and Critic for Deep Reinforcement Learning

Nov 07, 2023
Junmin Zhong, Ruofan Wu, Jennie Si

Viaarxiv icon

Continuous-Time Reinforcement Learning: New Design Algorithms with Theoretical Insights and Performance Guarantees

Jul 18, 2023
Brent A. Wallace, Jennie Si

Figure 1 for Continuous-Time Reinforcement Learning: New Design Algorithms with Theoretical Insights and Performance Guarantees
Figure 2 for Continuous-Time Reinforcement Learning: New Design Algorithms with Theoretical Insights and Performance Guarantees
Figure 3 for Continuous-Time Reinforcement Learning: New Design Algorithms with Theoretical Insights and Performance Guarantees
Figure 4 for Continuous-Time Reinforcement Learning: New Design Algorithms with Theoretical Insights and Performance Guarantees
Viaarxiv icon

Long N-step Surrogate Stage Reward to Reduce Variances of Deep Reinforcement Learning in Complex Problems

Oct 10, 2022
Junmin Zhong, Ruofan Wu, Jennie Si

Figure 1 for Long N-step Surrogate Stage Reward to Reduce Variances of Deep Reinforcement Learning in Complex Problems
Figure 2 for Long N-step Surrogate Stage Reward to Reduce Variances of Deep Reinforcement Learning in Complex Problems
Figure 3 for Long N-step Surrogate Stage Reward to Reduce Variances of Deep Reinforcement Learning in Complex Problems
Figure 4 for Long N-step Surrogate Stage Reward to Reduce Variances of Deep Reinforcement Learning in Complex Problems
Viaarxiv icon

Robotic Knee Tracking Control to Mimic the Intact Human Knee Profile Based on Actor-critic Reinforcement Learning

Jan 22, 2021
Ruofan Wu, Zhikai Yao, Jennie Si, He, Huang

Figure 1 for Robotic Knee Tracking Control to Mimic the Intact Human Knee Profile Based on Actor-critic Reinforcement Learning
Figure 2 for Robotic Knee Tracking Control to Mimic the Intact Human Knee Profile Based on Actor-critic Reinforcement Learning
Figure 3 for Robotic Knee Tracking Control to Mimic the Intact Human Knee Profile Based on Actor-critic Reinforcement Learning
Figure 4 for Robotic Knee Tracking Control to Mimic the Intact Human Knee Profile Based on Actor-critic Reinforcement Learning
Viaarxiv icon

Reinforcement Learning Enabled Automatic Impedance Control of a Robotic Knee Prosthesis to Mimic the Intact Knee Motion in a Co-Adapting Environment

Jan 10, 2021
Ruofan Wu, Minhan Li, Zhikai Yao, Jennie Si, He, Huang

Figure 1 for Reinforcement Learning Enabled Automatic Impedance Control of a Robotic Knee Prosthesis to Mimic the Intact Knee Motion in a Co-Adapting Environment
Figure 2 for Reinforcement Learning Enabled Automatic Impedance Control of a Robotic Knee Prosthesis to Mimic the Intact Knee Motion in a Co-Adapting Environment
Figure 3 for Reinforcement Learning Enabled Automatic Impedance Control of a Robotic Knee Prosthesis to Mimic the Intact Knee Motion in a Co-Adapting Environment
Figure 4 for Reinforcement Learning Enabled Automatic Impedance Control of a Robotic Knee Prosthesis to Mimic the Intact Knee Motion in a Co-Adapting Environment
Viaarxiv icon

A Data-Driven Reinforcement Learning Solution Framework for Optimal and Adaptive Personalization of a Hip Exoskeleton

Nov 11, 2020
Xikai Tu, Minhan Li, Ming Liu, Jennie Si, He, Huang

Figure 1 for A Data-Driven Reinforcement Learning Solution Framework for Optimal and Adaptive Personalization of a Hip Exoskeleton
Figure 2 for A Data-Driven Reinforcement Learning Solution Framework for Optimal and Adaptive Personalization of a Hip Exoskeleton
Figure 3 for A Data-Driven Reinforcement Learning Solution Framework for Optimal and Adaptive Personalization of a Hip Exoskeleton
Figure 4 for A Data-Driven Reinforcement Learning Solution Framework for Optimal and Adaptive Personalization of a Hip Exoskeleton
Viaarxiv icon

Reinforcement Learning Control of Robotic Knee with Human in the Loop by Flexible Policy Iteration

Jun 16, 2020
Xiang Gao, Jennie Si, Yue Wen, Minhan Li, He, Huang

Figure 1 for Reinforcement Learning Control of Robotic Knee with Human in the Loop by Flexible Policy Iteration
Figure 2 for Reinforcement Learning Control of Robotic Knee with Human in the Loop by Flexible Policy Iteration
Figure 3 for Reinforcement Learning Control of Robotic Knee with Human in the Loop by Flexible Policy Iteration
Figure 4 for Reinforcement Learning Control of Robotic Knee with Human in the Loop by Flexible Policy Iteration
Viaarxiv icon

Online Reinforcement Learning Control by Direct Heuristic Dynamic Programming: from Time-Driven to Event-Driven

Jun 16, 2020
Qingtao Zhao, Jennie Si, Jian Sun

Figure 1 for Online Reinforcement Learning Control by Direct Heuristic Dynamic Programming: from Time-Driven to Event-Driven
Figure 2 for Online Reinforcement Learning Control by Direct Heuristic Dynamic Programming: from Time-Driven to Event-Driven
Figure 3 for Online Reinforcement Learning Control by Direct Heuristic Dynamic Programming: from Time-Driven to Event-Driven
Figure 4 for Online Reinforcement Learning Control by Direct Heuristic Dynamic Programming: from Time-Driven to Event-Driven
Viaarxiv icon