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

arXiv cs.RO / 5/5/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

Reinforcement Learning（RL）はアルゴリズムやハイパーパラメータへの感度が高く、環境間での一般化ギャップが実運用の障害になっているが、個別設定がギャップへ与える寄与は定量的に分解されていなかった。
本研究は、ロボティクス環境でのRL性能をSHapley Additive exPlanations（SHAP）で評価し、各設定が一般化に与える影響を定量化する説明可能なフレームワークを提案している。
Shapley値と一般化可能性の関係を理論的に結び付け、実験で設定が与える影響のパターン（アルゴリズム／ハイパーパラメータ別の特徴）を分析した。
SHAPに基づく設定選択（SHAP-guided configuration selection）により、設定の選び方を改善してRLの一般化性能を高め、実務者向けの実行可能な指針を示した。

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.