- Titel
- Explainability in Deep Reinforcement Learning
- Zitierfähige Url:
- https://nbn-resolving.org/urn:nbn:de:bsz:14-qucosa2-938447
- Erstveröffentlichung
- 2024
- Datum der Einreichung
- 26.08.2024
- Datum der Verteidigung
- 19.09.2024
- Abstract (EN)
- With the combination of Reinforcement Learning (RL) and Artificial Neural Networks (ANNs), Deep Reinforcement Learning (DRL) agents are shifted towards being non-interpretable black-box models. Developers of DRL agents, however, could benefit from enhanced interpretability of the agents’ behavior, especially during the training process. Improved interpretability could enable developers to make informed adaptations, leading to better overall performance. The explainability methods Partial Dependence Plot (PDP), Accumulated Local Effects (ALE) and SHapley Additive exPlanations (SHAP) were considered to provide insights into how an agent’s behavior evolves during training. Additionally, a decision tree as a surrogate model was considered to enhance the interpretability of a trained agent. In a case study, the methods were tested on a Deep Deterministic Policy Gradient (DDPG) agent that was trained in an Obstacle Avoidance (OA) scenario. PDP, ALE and SHAP were evaluated towards their ability to provide explanations as well as the feasibility of their application in terms of computational overhead. The decision tree was evaluated towards its ability to approximate the agent’s policy as a post-hoc method. Results demonstrated that PDP, ALE and SHAP were able to provide valuable explanations during the training. Each method contributed additional information with their individual advantages. However, the decision tree failed to approximate the agent’s actions effectively to be used as a surrogate model.
- Freie Schlagwörter (EN)
- Explainability, Deep Reinforcement Learning, Feature Importance, Surrogate Model
- Klassifikation (DDC)
- 006
- Klassifikation (RVK)
- ST 300
- GutachterIn
- Prof. Dr. Ostap Okhrin
- Prof. Dr. Pascal Kerschke
- BetreuerIn Hochschule / Universität
- Dipl. Wi.-Ing. Martin Waltz
- Den akademischen Grad verleihende / prüfende Institution
- Technische Universität Dresden, Dresden
- Version / Begutachtungsstatus
- publizierte Version / Verlagsversion
- URN Qucosa
- urn:nbn:de:bsz:14-qucosa2-938447
- Veröffentlichungsdatum Qucosa
- 29.10.2024
- Dokumenttyp
- Masterarbeit / Staatsexamensarbeit
- Sprache des Dokumentes
- Englisch
- Lizenz / Rechtehinweis
CC BY 4.0- Inhaltsverzeichnis
List of Figures List of Tables List of Abbreviations 1 Introduction 2 Foundations 2.1 Machine Learning 2.1.1 Deep Learning 2.2 Reinforcement Learning 2.2.1 Markov Decision Process 2.2.2 Limitations of Optimal Solutions 2.2.3 Deep Reinforcement Learning 2.3 Explainability 2.3.1 Obstacles for Explainability Methods 3 Applied Explainability Methods 3.1 Real-Time Methods 3.1.1 Partial Dependence Plot 3.1.1.1 Incremental Partial Dependence Plots for Dynamic Modeling Scenarios 3.1.1.2 PDP-based Feature Importance 3.1.2 Accumulated Local Effects 3.1.3 SHapley Additive exPlanations 3.2 Post-Hoc Method: Global Surrogate Model 4 Case Study: Obstacle Avoidance 4.1 Environment Representation 4.2 Agent 4.3 Application Settings 5 Results 5.1 Problems of the Incremental Partial Dependence Plot 5.2 Real-Time Methods 5.2.1 Feature Importance 5.2.2 Computational Overhead 5.3 Global Surrogate Model 6 Discussion 7 Conclusion Bibliography Appendix A Incremental Partial Dependence Results