This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history generated by unknown behavioral policies. We study a regression-based fitted Q iteration method, and show that it is equivalent to a model-based method that estimates a conditional mean embedding of the transition operator. We prove that this method is information-theoretically optimal and has nearly minimal estimation error. In particular, by leveraging contraction property of Markov processes and martingale concentration, we establish a finite-sample instance-dependent error upper bound and a nearly-matching minimax lower bound. The policy evaluation error depends sharply on a restricted $\chi^2$-divergence over the function class between the long-term distribution of the target policy and the distribution of past data. This restricted $\chi^2$-divergence is both instance-dependent and function-class-dependent. It characterizes the statistical limit of off-policy evaluation. Further, we provide an easily computable confidence bound for the policy evaluator, which may be useful for optimistic planning and safe policy improvement.

本文研究利用函数逼近的批量数据强化学习的统计理论，针对离线策略评估问题提出了基于回归的适应Q迭代方法，证明该方法是信息理论上的最优方法，错误估计接近最小，进而提供容易计算的置信区间，该方法在乐观规划和安全策略改进中可能有用

线性函数逼近下的最小化最优离线策略评估