Variance-Aware Off-Policy Evaluation with Linear Function Approximation
–Neural Information Processing Systems
We study the off-policy evaluation (OPE) problem in reinforcement learning with linear function approximation, which aims to estimate the value function of a target policy based on the offline data collected by a behavior policy. We propose to incorporate the variance information of the value function to improve the sample efficiency of OPE. More specifically, for time-inhomogeneous episodic linear Markov decision processes (MDPs), we propose an algorithm, VA-OPE, which uses the estimated variance of the value function to reweight the Bellman residual in Fitted Q-Iteration. We show that our algorithm achieves a tighter error bound than the best-known result. We also provide a fine-grained characterization of the distribution shift between the behavior policy and the target policy. Extensive numerical experiments corroborate our theory.
Neural Information Processing Systems
Apr-25-2026, 14:03:45 GMT
- Country:
- North America > United States > California > Los Angeles County > Los Angeles (0.28)
- Genre:
- Research Report (0.46)
- Technology: