REVEAL-IT: REinforcement learning with Visibility of Evolving Agent poLicy for InTerpretability

TL;DR

REVEAL-IT introduces a framework that visualizes and explains agent learning in complex environments, using GNNs to highlight key policy components and improve training efficiency.

Contribution

The paper presents a novel visualization and explanation method for reinforcement learning agents in complex settings, extending interpretability beyond simple environments.

Findings

Effective visualization of policy structures in complex environments.

GNN-based explainer highlights critical policy sections.

Improved training efficiency and performance through explanations.

Abstract

Understanding the agent's learning process, particularly the factors that contribute to its success or failure post-training, is crucial for comprehending the rationale behind the agent's decision-making process. Prior methods clarify the learning process by creating a structural causal model (SCM) or visually representing the distribution of value functions. Nevertheless, these approaches have constraints as they exclusively function in 2D-environments or with uncomplicated transition dynamics. Understanding the agent's learning process in complicated environments or tasks is more challenging. In this paper, we propose REVEAL-IT, a novel framework for explaining the learning process of an agent in complex environments. Initially, we visualize the policy structure and the agent's learning process for various training tasks. By visualizing these findings, we can understand how much a particular training task or stage affects the agent's performance in test. Then, a GNN-based explainer learns to highlight the most important section of the policy, providing a more clear and robust explanation of the agent's learning process. The experiments demonstrate that explanations derived from this framework can effectively help in the optimization of the training tasks, resulting in improved learning efficiency and final performance.