Interpretable Deep Reinforcement Learning for Green Security Games with Real-Time Information

TL;DR

This paper introduces an interpretable deep reinforcement learning approach for green security games with real-time information, enhancing transparency and performance over existing methods.

Contribution

It proposes a novel interpretable DRL method for GSG-I that provides visual explanations and outperforms prior approaches with simpler training.

Findings

The method offers visual explanations of decisions.

It achieves better performance than existing approaches.

It requires a simpler training regimen.

Abstract

Green Security Games with real-time information (GSG-I) add the real-time information about the agents' movement to the typical GSG formulation. Prior works on GSG-I have used deep reinforcement learning (DRL) to learn the best policy for the agent in such an environment without any need to store the huge number of state representations for GSG-I. However, the decision-making process of DRL methods is largely opaque, which results in a lack of trust in their predictions. To tackle this issue, we present an interpretable DRL method for GSG-I that generates visualization to explain the decisions taken by the DRL algorithm. We also show that this approach performs better and works well with a simpler training regimen compared to the existing method.