Robust Offline Reinforcement learning with Heavy-Tailed Rewards
This work addresses robustness in offline RL for real-world applications where heavy-tailed rewards are common, representing an incremental improvement over existing methods.
The paper tackles the problem of offline reinforcement learning with heavy-tailed rewards by proposing two frameworks, ROAM and ROOM, for robust off-policy evaluation and optimization, which outperform existing methods on datasets with heavy-tailed reward distributions.
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 optimization (OPO), respectively. Central to our frameworks is the strategic incorporation of the median-of-means method with offline RL, enabling straightforward uncertainty estimation for the value function estimator. This not only adheres to the principle of pessimism in OPO but also adeptly manages heavy-tailed rewards. Theoretical results and extensive experiments demonstrate that our two frameworks outperform existing methods on the logged dataset exhibits heavy-tailed reward distributions. The implementation of the proposal is available at https://github.com/Mamba413/ROOM.