Picture for Fengdi Che

Fengdi Che

Equal Contribution

Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation

Add code
May 31, 2024
Viaarxiv icon

Correcting discount-factor mismatch in on-policy policy gradient methods

Add code
Jun 23, 2023
Viaarxiv icon

Bayesian Q-learning With Imperfect Expert Demonstrations

Add code
Oct 01, 2022
Figure 1 for Bayesian Q-learning With Imperfect Expert Demonstrations
Figure 2 for Bayesian Q-learning With Imperfect Expert Demonstrations
Figure 3 for Bayesian Q-learning With Imperfect Expert Demonstrations
Figure 4 for Bayesian Q-learning With Imperfect Expert Demonstrations
Viaarxiv icon

Detecting GAN generated errors

Add code
Dec 02, 2019
Figure 1 for Detecting GAN generated errors
Figure 2 for Detecting GAN generated errors
Figure 3 for Detecting GAN generated errors
Figure 4 for Detecting GAN generated errors
Viaarxiv icon