Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910189602471936 |
|---|---|
| author | Kong, Lingxiao Yang, Cong Beyan, Oya Deniz Boukhers, Zeyd |
| author_facet | Kong, Lingxiao Yang, Cong Beyan, Oya Deniz Boukhers, Zeyd |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02867 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters Kong, Lingxiao Yang, Cong Beyan, Oya Deniz Boukhers, Zeyd Machine Learning Artificial Intelligence Robotics 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. |
| title | Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters |
| topic | Machine Learning Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2605.02867 |