Resolving Spurious Correlations in Causal Models of Environments via Interventions

TL;DR

This paper introduces intervention-based methods to improve causal models in reinforcement learning environments by identifying and correcting spurious correlations, leading to more accurate and robust causal inference.

Contribution

It proposes novel intervention design strategies to resolve spurious correlations in causal models within reinforcement learning environments.

Findings

Intervention-based data improves causal model accuracy.

Methods outperform baseline approaches like random policy data.

Approach enhances model robustness and interpretability.

Abstract

Causal models bring many benefits to decision-making systems (or agents) by making them interpretable, sample-efficient, and robust to changes in the input distribution. However, spurious correlations can lead to wrong causal models and predictions. We consider the problem of inferring a causal model of a reinforcement learning environment and we propose a method to deal with spurious correlations. Specifically, our method designs a reward function that incentivizes an agent to do an intervention to find errors in the causal model. The data obtained from doing the intervention is used to improve the causal model. We propose several intervention design methods and compare them. The experimental results in a grid-world environment show that our approach leads to better causal models compared to baselines: learning the model on data from a random policy or a policy trained on the environment's reward. The main contribution consists of methods to design interventions to resolve spurious correlations.