Picture for Kuangen Zhang

Kuangen Zhang

Ensemble diverse hypotheses and knowledge distillation for unsupervised cross-subject adaptation

Add code
Apr 15, 2022
Figure 1 for Ensemble diverse hypotheses and knowledge distillation for unsupervised cross-subject adaptation
Figure 2 for Ensemble diverse hypotheses and knowledge distillation for unsupervised cross-subject adaptation
Figure 3 for Ensemble diverse hypotheses and knowledge distillation for unsupervised cross-subject adaptation
Figure 4 for Ensemble diverse hypotheses and knowledge distillation for unsupervised cross-subject adaptation
Viaarxiv icon

Preserving Domain Private Representation via Mutual Information Maximization

Add code
Jan 09, 2022
Figure 1 for Preserving Domain Private Representation via Mutual Information Maximization
Figure 2 for Preserving Domain Private Representation via Mutual Information Maximization
Figure 3 for Preserving Domain Private Representation via Mutual Information Maximization
Figure 4 for Preserving Domain Private Representation via Mutual Information Maximization
Viaarxiv icon

How does the structure embedded in learning policy affect learning quadruped locomotion?

Add code
Aug 29, 2020
Figure 1 for How does the structure embedded in learning policy affect learning quadruped locomotion?
Figure 2 for How does the structure embedded in learning policy affect learning quadruped locomotion?
Figure 3 for How does the structure embedded in learning policy affect learning quadruped locomotion?
Figure 4 for How does the structure embedded in learning policy affect learning quadruped locomotion?
Viaarxiv icon

Off-policy Maximum Entropy Reinforcement Learning : Soft Actor-Critic with Advantage Weighted Mixture Policy(SAC-AWMP)

Add code
Feb 07, 2020
Figure 1 for Off-policy Maximum Entropy Reinforcement Learning : Soft Actor-Critic with Advantage Weighted Mixture Policy(SAC-AWMP)
Figure 2 for Off-policy Maximum Entropy Reinforcement Learning : Soft Actor-Critic with Advantage Weighted Mixture Policy(SAC-AWMP)
Figure 3 for Off-policy Maximum Entropy Reinforcement Learning : Soft Actor-Critic with Advantage Weighted Mixture Policy(SAC-AWMP)
Figure 4 for Off-policy Maximum Entropy Reinforcement Learning : Soft Actor-Critic with Advantage Weighted Mixture Policy(SAC-AWMP)
Viaarxiv icon

Teach Biped Robots to Walk via Gait Principles and Reinforcement Learning with Adversarial Critics

Add code
Oct 22, 2019
Figure 1 for Teach Biped Robots to Walk via Gait Principles and Reinforcement Learning with Adversarial Critics
Figure 2 for Teach Biped Robots to Walk via Gait Principles and Reinforcement Learning with Adversarial Critics
Figure 3 for Teach Biped Robots to Walk via Gait Principles and Reinforcement Learning with Adversarial Critics
Figure 4 for Teach Biped Robots to Walk via Gait Principles and Reinforcement Learning with Adversarial Critics
Viaarxiv icon

Sequential Decision Fusion for Environmental Classification in Assistive Walking

Add code
Apr 25, 2019
Figure 1 for Sequential Decision Fusion for Environmental Classification in Assistive Walking
Figure 2 for Sequential Decision Fusion for Environmental Classification in Assistive Walking
Figure 3 for Sequential Decision Fusion for Environmental Classification in Assistive Walking
Figure 4 for Sequential Decision Fusion for Environmental Classification in Assistive Walking
Viaarxiv icon

Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features

Add code
Apr 22, 2019
Figure 1 for Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
Figure 2 for Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
Figure 3 for Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
Figure 4 for Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
Viaarxiv icon

Sensor Fusion for Predictive Control of Human-Prosthesis-Environment Dynamics in Assistive Walking: A Survey

Add code
Mar 22, 2019
Figure 1 for Sensor Fusion for Predictive Control of Human-Prosthesis-Environment Dynamics in Assistive Walking: A Survey
Figure 2 for Sensor Fusion for Predictive Control of Human-Prosthesis-Environment Dynamics in Assistive Walking: A Survey
Figure 3 for Sensor Fusion for Predictive Control of Human-Prosthesis-Environment Dynamics in Assistive Walking: A Survey
Figure 4 for Sensor Fusion for Predictive Control of Human-Prosthesis-Environment Dynamics in Assistive Walking: A Survey
Viaarxiv icon

Unsupervised Domain Adaptation Learning Algorithm for RGB-D Staircase Recognition

Add code
Mar 20, 2019
Viaarxiv icon

Directional PointNet: 3D Environmental Classification for Wearable Robotics

Add code
Mar 20, 2019
Viaarxiv icon