Picture for Jiayu Yao

Jiayu Yao

Contextual Conservative Q-Learning for Offline Reinforcement Learning

Jan 16, 2023
Figure 1 for Contextual Conservative Q-Learning for Offline Reinforcement Learning
Figure 2 for Contextual Conservative Q-Learning for Offline Reinforcement Learning
Figure 3 for Contextual Conservative Q-Learning for Offline Reinforcement Learning
Figure 4 for Contextual Conservative Q-Learning for Offline Reinforcement Learning
Viaarxiv icon

Deep Semi-supervised Learning with Double-Contrast of Features and Semantics

Nov 28, 2022
Figure 1 for Deep Semi-supervised Learning with Double-Contrast of Features and Semantics
Figure 2 for Deep Semi-supervised Learning with Double-Contrast of Features and Semantics
Figure 3 for Deep Semi-supervised Learning with Double-Contrast of Features and Semantics
Figure 4 for Deep Semi-supervised Learning with Double-Contrast of Features and Semantics
Viaarxiv icon

An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks

Add code
Nov 28, 2022
Figure 1 for An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks
Figure 2 for An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks
Figure 3 for An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks
Figure 4 for An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks
Viaarxiv icon

Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry

Aug 05, 2022
Figure 1 for Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry
Figure 2 for Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry
Figure 3 for Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry
Figure 4 for Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry
Viaarxiv icon

Policy Optimization with Sparse Global Contrastive Explanations

Jul 13, 2022
Figure 1 for Policy Optimization with Sparse Global Contrastive Explanations
Figure 2 for Policy Optimization with Sparse Global Contrastive Explanations
Figure 3 for Policy Optimization with Sparse Global Contrastive Explanations
Figure 4 for Policy Optimization with Sparse Global Contrastive Explanations
Viaarxiv icon

Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts

Apr 11, 2022
Figure 1 for Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts
Figure 2 for Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts
Figure 3 for Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts
Figure 4 for Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts
Viaarxiv icon

Power-Constrained Bandits

Add code
Apr 13, 2020
Figure 1 for Power-Constrained Bandits
Figure 2 for Power-Constrained Bandits
Figure 3 for Power-Constrained Bandits
Figure 4 for Power-Constrained Bandits
Viaarxiv icon

Quality of Uncertainty Quantification for Bayesian Neural Network Inference

Add code
Jun 24, 2019
Figure 1 for Quality of Uncertainty Quantification for Bayesian Neural Network Inference
Figure 2 for Quality of Uncertainty Quantification for Bayesian Neural Network Inference
Figure 3 for Quality of Uncertainty Quantification for Bayesian Neural Network Inference
Figure 4 for Quality of Uncertainty Quantification for Bayesian Neural Network Inference
Viaarxiv icon

Output-Constrained Bayesian Neural Networks

Add code
May 15, 2019
Figure 1 for Output-Constrained Bayesian Neural Networks
Figure 2 for Output-Constrained Bayesian Neural Networks
Figure 3 for Output-Constrained Bayesian Neural Networks
Figure 4 for Output-Constrained Bayesian Neural Networks
Viaarxiv icon

Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights

Add code
Dec 03, 2018
Figure 1 for Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights
Figure 2 for Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights
Figure 3 for Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights
Figure 4 for Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights
Viaarxiv icon