Heterogeneous Knowledge For Augmented Modular Reinforcement Learning

Abstract

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywolf2023heterogeneous

Related papers

• Integrating Distributed Architectures In Highly Modular RL Libraries (2020)0.00
• Heterogeneous-agent Reinforcement Learning (2023)0.00
• Knowsr: Knowledge Sharing Among Homogeneous Agents In Multi-agent Reinforcement Learning (2021)0.00
• Foundations For Transfer In Reinforcement Learning: A Taxonomy Of Knowledge Modalities (2023)0.00
• Heterogeneous Multi-robot Reinforcement Learning (2023)6.77
• HMRL: Hyper-meta Learning For Sparse Reward Reinforcement Learning Problem (2020)0.00
• Hypermarl: Adaptive Hypernetworks For Multi-agent RL (2024)0.00
• Leveraging Approximate Symbolic Models For Reinforcement Learning Via Skill Diversity (2022)0.00