Recent theoretical work studies sample-efficient reinforcement learning (RL) extensively in two settings: learning interactively in the environment (online RL), or learning from an offline dataset (offline RL). However, existing algorithms and theories for learning near-optimal policies in these two settings are rather different and disconnected. Towards bridging this gap, this paper initiates the theoretical study of policy finetuning, that is, online RL where the learner has additional access to a reference policy $mu$ close to the optimal policy $pi_star$ in a certain sense. We consider the policy finetuning problem in episodic Markov Decision Processes (MDPs) with $S$ states, $A$ actions, and horizon length $H$. We first design a sharp offline reduction algorithm -- which simply executes $mu$ and runs offline policy optimization on the collected dataset -- that finds an $varepsilon$ near-optimal policy within $widetilde{O}(H^3SC^star/varepsilon^2)$ episodes, where $C^star$ is the single-policy concentrability coefficient between $mu$ and $pi_star$. This offline result is the first that matches the sample complexity lower bound in this setting, and resolves a recent open question in offline RL. We then establish an $Omega(H^3Smin{C^star, A}/varepsilon^2)$ sample complexity lower bound for any policy finetuning algorithm, including those that can adaptively explore the environment. This implies that -- perhaps surprisingly -- the optimal policy finetuning algorithm is either offline reduction or a purely online RL algorithm that does not use $mu$. Finally, we design a new hybrid offline/online algorithm for policy finetuning that achieves better sample complexity than both vanilla offline reduction and purely online RL algorithms, in a relaxed setting where $mu$ only satisfies concentrability partially up to a certain time step.
تحميل البحث