Pay Attention to What and Where? Interpretable Feature Extractor in Vision-based Deep Reinforcement Learning
This addresses the spatial misalignment issue in explainable deep reinforcement learning for vision-based agents, offering an incremental improvement in interpretability.
The paper tackled the problem of attention masks being misaligned with objects in visual inputs for explainable deep reinforcement learning, proposing an Interpretable Feature Extractor (IFE) that generates accurate and human-understandable attention masks, evaluated on 57 ATARI games to show effectiveness in spatial preservation, interpretability, and data-efficiency.
Current approaches in Explainable Deep Reinforcement Learning have limitations in which the attention mask has a displacement with the objects in visual input. This work addresses a spatial problem within traditional Convolutional Neural Networks (CNNs). We propose the Interpretable Feature Extractor (IFE) architecture, aimed at generating an accurate attention mask to illustrate both "what" and "where" the agent concentrates on in the spatial domain. Our design incorporates a Human-Understandable Encoding module to generate a fully interpretable attention mask, followed by an Agent-Friendly Encoding module to enhance the agent's learning efficiency. These two components together form the Interpretable Feature Extractor for vision-based deep reinforcement learning to enable the model's interpretability. The resulting attention mask is consistent, highly understandable by humans, accurate in spatial dimension, and effectively highlights important objects or locations in visual input. The Interpretable Feature Extractor is integrated into the Fast and Data-efficient Rainbow framework, and evaluated on 57 ATARI games to show the effectiveness of the proposed approach on Spatial Preservation, Interpretability, and Data-efficiency. Finally, we showcase the versatility of our approach by incorporating the IFE into the Asynchronous Advantage Actor-Critic Model.