[2605.02867] Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters

Computer Science > Machine Learning arXiv:2605.02867 (cs) [Submitted on 4 May 2026] Title:Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters Authors:Lingxiao Kong, Cong Yang, Oya Deniz Beyan, Zeyd Boukhers View a PDF of the paper titled Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters, by Lingxiao Kong and 3 other authors View PDF HTML (experimental) 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 th...