Scaling Online Distributionally Robust Reinforcement Learning: Sample-Efficient Guarantees with General Function Approximation

The deployment of reinforcement learning (RL) agents in real-world applications is often hindered by performance degradation caused by mismatches between training and deployment environments. Distributionally robust RL (DR-RL) addresses this issue by optimizing worst-case performance over an uncertainty set of transition dynamics. However, existing work typically relies on substantial prior knowledge-such as access to a generative model or a large offline dataset-and largely focuses on tabular methods that do not scale to complex domains. We overcome these limitations by proposing an online DR-RL algorithm with general function approximation that learns an optimal robust policy purely through interaction with the environment, without requiring prior models or offline data, enabling deployment in high-dimensional tasks. We further provide a theoretical analysis establishing a near-optimal sublinear regret bound under a total variation uncertainty set, demonstrating the sample efficiency and effectiveness of our method.