Robust Offline Reinforcement learning with Heavy-Tailed Rewards

• Main Authors: Zhu, Jin, Wan, Runzhe, Qi, Zhengling, Luo, Shikai, Shi, Chengchun
• Format: Journal Article
• Language: English
• Published: 28.10.2023
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Learning; Statistics - Machine Learning

This paper endeavors to augment the robustness of offline reinforcement learning (RL) in scenarios laden with heavy-tailed rewards, a prevalent circumstance in real-world applications. We propose two algorithmic frameworks, ROAM and ROOM, for robust off-policy evaluation and offline policy optimizat...