Picture for Seungyub Han

Seungyub Han

Tractable and Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation

Add code
Jul 31, 2024
Viaarxiv icon

Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees

Add code
May 29, 2024
Figure 1 for Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
Figure 2 for Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
Figure 3 for Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
Figure 4 for Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
Viaarxiv icon

On the Convergence of Continual Learning with Adaptive Methods

Add code
Apr 15, 2024
Viaarxiv icon

SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning

Add code
Jan 06, 2024
Viaarxiv icon

Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion

Add code
Oct 27, 2023
Viaarxiv icon

Learning to Learn Unlearned Feature for Brain Tumor Segmentation

Add code
May 13, 2023
Viaarxiv icon