Picture for Duksang Lee

Duksang Lee

Improved Regret Bound for Safe Reinforcement Learning via Tighter Cost Pessimism and Reward Optimism

Add code
Oct 14, 2024
Viaarxiv icon

Online Resource Allocation in Episodic Markov Decision Processes

Add code
May 18, 2023
Viaarxiv icon

Projection-Free Online Convex Optimization with Stochastic Constraints

Add code
May 02, 2023
Viaarxiv icon