Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks and Autoregressive Policy Decomposition

2020/09/25 by Jaromír Janisch, Janisch, Jaromír, Tomáš Pevný +3
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.2009.12462

openalex publication_date 2020/09/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We focus on reinforcement learning (RL) in relational problems that are naturally defined in terms of objects, their relations, and object-centric actions. These problems are characterized by variable state and action spaces, and finding a fixed-length representation, required by most existing RL methods, is difficult, if not impossible. We present a deep RL framework based on graph neural networks and auto-regressive policy decomposition that naturally works with these problems and is completely domain-independent. We demonstrate the framework's broad applicability in three distinct domains and show impressive zero-shot generalization over different problem sizes.

Related

• Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach
• Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems
• Human-Allied Relational Reinforcement Learning
• Relational Deep Reinforcement Learning
• Relational-Grid-World: A Novel Relational Reasoning Environment and An Agent Model for Relational Information Extraction