Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
This work addresses the challenge for AI agents, such as robots, in learning high-level causal variables from raw sensory data, though it is incremental as it focuses on benchmarking rather than a new method.
The authors tackled the problem of jointly discovering abstract representations and causal structures from low-level observations in reinforcement learning by designing a suite of benchmarking environments to systematically evaluate methods, finding that incorporating structure and modularity in models aids causal induction.
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.