Jonathan Lee

Latest

• Estimating Optimal Policy Value in General Linear Contextual Bandits
• Dueling RL: Reinforcement Learning with Trajectory Preferences
• Near Optimal Policy Optimization via REPS
• Accelerated Message Passing for Entropy-Regularized MAP Inference
• Online Model Selection for Reinforcement Learning with Function Approximation
• Convergence Rates of Smooth Message Passing with Rounding in Entropy-Regularized MAP Inference