Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters
For RL practitioners, this work provides a method to systematically select configurations that enhance generalization, addressing a key bottleneck in real-world deployment.
The paper proposes a SHAP-based framework to quantify the impact of algorithm and hyperparameter configurations on RL generalization, and shows that SHAP-guided configuration selection improves generalizability across robotic environments.
Despite significant advances in Reinforcement Learning (RL), model performance remains highly sensitive to algorithm and hyperparameter configurations, while generalization gaps across environments complicate real-world deployment. Although prior work has studied RL generalization, the relative contribution of specific configurations to the generalization gap has not been quantitatively decomposed and systematically leveraged for configuration selection. To address this limitation, we propose an explainable framework that evaluates RL performance across robotic environments using SHapley Additive exPlanations (SHAP) to quantify configuration impacts. We establish a theoretical foundation connecting Shapley values to generalizability, empirically analyze configuration impact patterns, and introduce SHAP-guided configuration selection to enhance generalization. Our results reveal distinct patterns across algorithms and hyperparameters, with consistent configuration impacts across diverse tasks and environments. By applying these insights to configuration selection, we achieve improved RL generalizability and provide actionable guidance for practitioners.