Stochastic Intervention for Causal Inference via Reinforcement Learning

TL;DR

This paper introduces a novel framework for causal inference under stochastic interventions, utilizing a nonparametric influence function estimator and a reinforcement learning algorithm to optimize treatment policies with theoretical guarantees.

Contribution

It advances causal inference by enabling treatment effect estimation for stochastic interventions and develops a reinforcement learning method to find optimal policies.

Findings

The proposed estimator is robust with fast convergence.

The reinforcement learning algorithm effectively identifies optimal policies.

Empirical results outperform state-of-the-art baselines.

Abstract

Causal inference methods are widely applied in various decision-making domains such as precision medicine, optimal policy and economics. Central to causal inference is the treatment effect estimation of intervention strategies, such as changes in drug dosing and increases in financial aid. Existing methods are mostly restricted to the deterministic treatment and compare outcomes under different treatments. However, they are unable to address the substantial recent interest of treatment effect estimation under stochastic treatment, e.g., "how all units health status change if they adopt 50\% dose reduction". In other words, they lack the capability of providing fine-grained treatment effect estimation to support sound decision-making. In our study, we advance the causal inference research by proposing a new effective framework to estimate the treatment effect on stochastic intervention. Particularly, we develop a stochastic intervention effect estimator (SIE) based on nonparametric influence function, with the theoretical guarantees of robustness and fast convergence rates. Additionally, we construct a customised reinforcement learning algorithm based on the random search solver which can effectively find the optimal policy to produce the greatest expected outcomes for the decision-making process. Finally, we conduct an empirical study to justify that our framework can achieve significant performance in comparison with state-of-the-art baselines.