Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters
2026-05-04 • Machine Learning
Machine LearningArtificial IntelligenceRobotics
AI summaryⓘ
The authors looked at why reinforcement learning (RL) models sometimes perform well in training but not in new environments. They used a method called SHAP to explain how different settings (like algorithms and hyperparameters) affect performance and generalization. By studying these effects, they found consistent patterns and used them to pick better configurations that improve how well RL models work in different tasks. This helps make RL more reliable and easier to apply in real-world robotic environments.
Reinforcement LearningGeneralizationHyperparametersAlgorithmsSHapley Additive exPlanations (SHAP)RoboticsModel PerformanceConfiguration Selection
Authors
Lingxiao Kong, Cong Yang, Oya Deniz Beyan, Zeyd Boukhers
Abstract
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.