Bias and Variance Approximation in Value Function Estimates
Shie Mannor, Duncan Simester, Peng Sun, John N. Tsitsiklis
Management Science · 2007 · Volume 53 · Issue 2
Abstract
We consider a finite-state, finite-action, infinite-horizon, discounted reward Markov decision process and study the bias and variance in the value function estimates that result from empirical estimates of the model parameters. We provide closed-form approximations for the bias and variance, which can then be used to derive confidence intervals around the value function estimates. We illustrate and validate our findings using a large database describing the transaction and mailing histories for customers of a mail-order catalog firm.
Keywords
value function, confidence interval, variance, bias
Enable JavaScript for citation tools and additional paper interactions.