From Generative to Episodic: Sample-Efficient Replicable Reinforcement Learning
This work addresses the replicability crisis in reinforcement learning, providing a foundational advance for researchers in theoretical ML and AI by enabling sample-efficient replicable learning without a generative model.
The paper tackles the problem of replicable reinforcement learning in episodic settings, showing that exploration is not a significant barrier by developing an algorithm that achieves near-optimal sample efficiency with O~(S^2A) samples, matching lower bounds and bridging the gap between generative and episodic settings.
The epidemic failure of replicability across empirical science and machine learning has recently motivated the formal study of replicable learning algorithms [Impagliazzo et al. (2022)]. In batch settings where data comes from a fixed i.i.d. source (e.g., hypothesis testing, supervised learning), the design of data-efficient replicable algorithms is now more or less understood. In contrast, there remain significant gaps in our knowledge for control settings like reinforcement learning where an agent must interact directly with a shifting environment. Karbasi et. al show that with access to a generative model of an environment with $S$ states and $A$ actions (the RL 'batch setting'), replicably learning a near-optimal policy costs only $\tilde{O}(S^2A^2)$ samples. On the other hand, the best upper bound without a generative model jumps to $\tilde{O}(S^7 A^7)$ [Eaton et al. (2024)] due to the substantial difficulty of environment exploration. This gap raises a key question in the broader theory of replicability: Is replicable exploration inherently more expensive than batch learning? Is sample-efficient replicable RL even possible? In this work, we (nearly) resolve this problem (for low-horizon tabular MDPs): exploration is not a significant barrier to replicable learning! Our main result is a replicable RL algorithm on $\tilde{O}(S^2A)$ samples, bridging the gap between the generative and episodic settings. We complement this with a matching $\tildeΩ(S^2A)$ lower bound in the generative setting (under the common parallel sampling assumption) and an unconditional lower bound in the episodic setting of $\tildeΩ(S^2)$ showcasing the near-optimality of our algorithm with respect to the state space $S$.