Sample-Efficient Neurosymbolic Deep Reinforcement Learning

Reinforcement Learning (RL) provides a standard framework for sequential decision-making, but state-of-the-art Deep RL (DRL) methods are often sample-inefficient and struggle to generalize beyond small-scale training scenarios. We propose a neuro-symbolic DRL approach that integrates background symbolic knowledge to improve sample efficiency and generalization to more complex, unseentasks. Partialpolicieslearnedinsimpledomainsaretransferred as logical rules and used for online reasoning to guide learning by biasingexplorationandrescalingQ-valuesduringexploitation. This integration enhances interpretability and accelerates convergence, particularly in sparse-reward and long-horizon settings. Experiments show superior performance over state-of-the-art reward machine methods.

Authors

• Celeste Veronese University of Verona
• Alessandro Farinelli University of Verona
• Daniele Meli University of Verona

Keywords

• Neurosymbolic RL
• Knowledge Transfer
• Sample Efficiency