Part of Advances in Neural Information Processing Systems 35 (NeurIPS 2022) Main Conference Track
Rujie Zhong, Duohan Zhang, Lukas Schäfer, Stefano Albrecht, Josiah Hanna
Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy. In this paper, we study a subtle distinction between on-policy data and on-policy sampling in the context of the RL sub-problem of policy evaluation. We observe that on-policy sampling may fail to match the expected distribution of on-policy data after observing only a finite number of trajectories and this failure hinders data-efficient policy evaluation. Towards improved data-efficiency, we show how non-i.i.d., off-policy sampling can produce data that more closely matches the expected on-policy data distribution and consequently increases the accuracy of the Monte Carlo estimator for policy evaluation. We introduce a method called Robust On-Policy Sampling and demonstrate theoretically and empirically that it produces data that converges faster to the expected on-policy distribution compared to on-policy sampling. Empirically, we show that this faster convergence leads to lower mean squared error policy value estimates.