State Relevance for Off-Policy Evaluation
This work addresses variance reduction in off-policy evaluation for reinforcement learning, presenting an incremental improvement over existing methods.
The paper tackles the high variance problem in importance sampling-based off-policy evaluation, especially for trajectories of varying lengths, by introducing OSIRIS, which reduces variance by omitting certain state likelihood ratios while maintaining unbiasedness, as demonstrated empirically.
Importance sampling-based estimators for off-policy evaluation (OPE) are valued for their simplicity, unbiasedness, and reliance on relatively few assumptions. However, the variance of these estimators is often high, especially when trajectories are of different lengths. In this work, we introduce Omitting-States-Irrelevant-to-Return Importance Sampling (OSIRIS), an estimator which reduces variance by strategically omitting likelihood ratios associated with certain states. We formalize the conditions under which OSIRIS is unbiased and has lower variance than ordinary importance sampling, and we demonstrate these properties empirically.