Skip to content

Opening book details…

Can I read Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders on EtoBox?

Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders by Bruns-Smith, David; Zhou, Angela is a scholarly article available to read on EtoBox.

What is Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders about?

Offline reinforcement learning is important in domains such as medicine, economics, and e-commerce where online experimentation is costly, dangerous or unethical, and where the true model is unknown. However, most methods assume all covariates used in the behavior policy's action decisions are observed. Though this assumption, sequential ignorability/unconfoundedness, likely does not hold in observational data, most of the data that accounts for selection into treatment may be observed, motivating sensitivity analysis. We study robust policy evaluation and policy optimization in the presence of sequentially-exogenous unobserved confounders under a sensitivity model. We propose and analyze orthogonalized robust fitted-Q-iteration that uses closed-form solutions of the robust Bellman operator to derive a loss minimization problem for the robust Q function, and adds a bias-correction to quantile estimation. Our algorithm enjoys the computational ease of fitted-Q-iteration and statistical improvements (reduced dependence on quantile estimation error) from orthogonalization. We provide sample complexity bounds, insights, and show effectiveness both in simulations and on real-world longi

Author
Bruns-Smith, David; Zhou, Angela
Published
2023
Language
EN

More by Bruns-Smith, David; Zhou, Angela

Browse all works by Bruns-Smith, David; Zhou, Angela