Picture for Chen-Yu Wei

Chen-Yu Wei

Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data

Mar 25, 2024
Viaarxiv icon

Tractable Local Equilibria in Non-Concave Games

Mar 13, 2024
Figure 1 for Tractable Local Equilibria in Non-Concave Games
Figure 2 for Tractable Local Equilibria in Non-Concave Games
Figure 3 for Tractable Local Equilibria in Non-Concave Games
Figure 4 for Tractable Local Equilibria in Non-Concave Games
Viaarxiv icon

Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games

Jan 26, 2024
Viaarxiv icon

Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback

Oct 17, 2023
Viaarxiv icon

Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits

Sep 02, 2023
Figure 1 for Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits
Viaarxiv icon

Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs

Jun 20, 2023
Figure 1 for Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
Figure 2 for Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
Figure 3 for Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
Figure 4 for Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
Viaarxiv icon

No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions

May 30, 2023
Viaarxiv icon

First- and Second-Order Bounds for Adversarial Linear Contextual Bandits

May 01, 2023
Viaarxiv icon

Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games

Mar 05, 2023
Figure 1 for Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games
Viaarxiv icon

A Blackbox Approach to Best of Both Worlds in Bandits and Beyond

Feb 20, 2023
Figure 1 for A Blackbox Approach to Best of Both Worlds in Bandits and Beyond
Viaarxiv icon