Heterogeneous Knowledge for Augmented Modular Reinforcement Learning
This addresses the problem of limited information processing in modular RL for AI researchers, though it appears incremental as it builds on existing modular architectures.
The paper tackles the limitation of homogeneous modules in modular Reinforcement Learning by proposing Augmented Modular Reinforcement Learning (AMRL) to integrate heterogeneous knowledge like rules and skills, resulting in performance and efficiency improvements with better generalization.
Existing modular Reinforcement Learning (RL) architectures are generally based on reusable components, also allowing for "plug-and-play" integration. However, these modules are homogeneous in nature - in fact, they essentially provide policies obtained via RL through the maximization of individual reward functions. Consequently, such solutions still lack the ability to integrate and process multiple types of information (i.e., heterogeneous knowledge representations), such as rules, sub-goals, and skills from various sources. In this paper, we discuss several practical examples of heterogeneous knowledge and propose Augmented Modular Reinforcement Learning (AMRL) to address these limitations. Our framework uses a selector to combine heterogeneous modules and seamlessly incorporate different types of knowledge representations and processing mechanisms. Our results demonstrate the performance and efficiency improvements, also in terms of generalization, that can be achieved by augmenting traditional modular RL with heterogeneous knowledge sources and processing mechanisms. Finally, we examine the safety, robustness, and interpretability issues stemming from the introduction of knowledge heterogeneity.