Picture for Yang Bo

Yang Bo

Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy Optimization

Add code
Sep 02, 2024
Figure 1 for Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy Optimization
Figure 2 for Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy Optimization
Figure 3 for Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy Optimization
Figure 4 for Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy Optimization
Viaarxiv icon

Confidence Adaptive Regularization for Deep Learning with Noisy Labels

Add code
Sep 05, 2021
Figure 1 for Confidence Adaptive Regularization for Deep Learning with Noisy Labels
Figure 2 for Confidence Adaptive Regularization for Deep Learning with Noisy Labels
Figure 3 for Confidence Adaptive Regularization for Deep Learning with Noisy Labels
Figure 4 for Confidence Adaptive Regularization for Deep Learning with Noisy Labels
Viaarxiv icon

Co-matching: Combating Noisy Labels by Augmentation Anchoring

Add code
Mar 23, 2021
Figure 1 for Co-matching: Combating Noisy Labels by Augmentation Anchoring
Figure 2 for Co-matching: Combating Noisy Labels by Augmentation Anchoring
Figure 3 for Co-matching: Combating Noisy Labels by Augmentation Anchoring
Figure 4 for Co-matching: Combating Noisy Labels by Augmentation Anchoring
Viaarxiv icon

CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition

Add code
Mar 18, 2021
Figure 1 for CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition
Figure 2 for CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition
Figure 3 for CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition
Figure 4 for CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition
Viaarxiv icon