Off-policy evaluation of sequential decision policies from observational data is necessary in applications of batch reinforcement learning such as education and healthcare. In such settings, however, observed actions are often confounded with transitions by unobserved variables, rendering exact evaluation of new policies impossible, i.e., unidentifiable. We develop a robust approach that estimates sharp bounds on the (unidentifiable) value of a given policy in an infinite-horizon problem given data from another policy with unobserved confounding subject to a sensitivity model. We phrase the problem precisely as computing the support function of the set of all stationary state-occupancy ratios that agree with both the data and the sensitivity model. We show how to express this set using a new partially identified estimating equation and prove convergence to the sharp bounds, as we collect more confounded data. We prove that membership in the set can be checked by solving a linear program, while the support function is given by a difficult nonconvex optimization problem. We leverage an analytical solution for the finite-state-space case to develop approximations based on nonconvex projected gradient descent. We demonstrate the resulting bounds empirically.

通过数据策略辅助下的敏感性模型，我们开发了一种强健的方法，针对诸如教育和医疗等批量强化学习的应用中未被观察到的变量，估计了一个无限时间阶段内给定策略值的尖锐边界。我们证明，随着我们收集更多混淆数据，我们能够收敛于尖锐的边界。虽然检查集合成员身份是一个线性规划，但支持功能是由一个困难的非凸优化问题给出的。我们基于非凸投影梯度下降方法开发了一些近似，并在实证中演示了所得到的边界。

无限时间序列强化学习中具有混淆鲁棒性的策略评估