Shie Mannor

9

Papers

1

Total Citations

Papers (9)

On the Convergence of Single-Timescale Actor-Critic

NeurIPS 2025arXiv

Reinforcement Learning with Segment Feedback

Improving Token-Based World Models with Parallel Observation Prediction

Sobolev Space Regularised Pre Density Models

Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization

Efficient Value Iteration for s-rectangular Robust Markov Decision Processes

Prospective Side Information for Latent MDPs

RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression

Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel