Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning

TL;DR

This paper introduces a benchmarking suite for evaluating causal discovery in visual reinforcement learning, emphasizing the importance of high-level causal representations from low-level observations and assessing different algorithms' effectiveness.

Contribution

It presents a systematic benchmarking environment for causal discovery in RL and analyzes how structured, modular models improve causal induction.

Findings

Structured models enhance causal discovery in RL.

Benchmark environments facilitate systematic evaluation.

Explicit structure incorporation aids causal induction.

Abstract

Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the premise that the causal variables themselves are observed. However, for AI agents such as robots trying to make sense of their environment, the only observables are low-level variables like pixels in images. To generalize well, an agent must induce high-level variables, particularly those which are causal or are affected by causal variables. A central goal for AI and causality is thus the joint discovery of abstract representations and causal structure. However, we note that existing environments for studying causal induction are poorly suited for this objective because they have complicated task-specific causal graphs which are impossible to manipulate parametrically (e.g., number of nodes, sparsity, causal chain length, etc.). In this work, our goal is to facilitate research in learning representations of high-level variables as well as causal structures among them. In order to systematically probe the ability of methods to identify these variables and structures, we design a suite of benchmarking RL environments. We evaluate various representation learning algorithms from the literature and find that explicitly incorporating structure and modularity in models can help causal induction in model-based reinforcement learning.