Advanced Automation for Comprehensible Causal Explanations of Reinforcement Learning Agents

Rudy Milani (Autor)

Buch | Softcover

2026
Springer Fachmedien Wiesbaden GmbH (Verlag)
978-3-658-50494-6 (ISBN)

Noch nicht erschienen - erscheint am 08.02.2026
Versandkostenfrei
Auch auf Rechnung

Artikel merken

This thesis introduces Auto-BENEDICT, a novel, fully automated methodology designed to generate human-comprehensible causal explanations for model-free Reinforcement Learning (RL) agents. The system addresses the trade-off between high performance and transparency in RL by integrating Bayesian Networks for causal inference and Recurrent Neural Networks to forecast future states and actions. The method provides answers to both Why and Why not questions, thereby increasing user trust and interpretability. The work also introduces enhanced importance metrics including both Q-value-based and graph-based approaches used to detect distal information, i.e., critical sequences of states or actions that are key to solving a task. These metrics are then fused with the causal explanation framework, resulting in Auto-BENEDICT, which not only explains but also recognizes high-risk or critical states automatically. Validation through computational experiments and a human evaluation study shows that Auto-BENEDICT significantly outperforms traditional methods in comprehensibility and trustworthiness, contributing a major advancement in Explainable Reinforcement Learning.

Rudy Milani obtained his Dr. rer. nat. in 2025 in Explainable Reinforcement Learning from the Universität der Bundeswehr München as a member of the COMTESSA research group. His work focuses on reinforcement learning, mathematical modelling, and optimization, combining theoretical insights with practical applications.

Erscheint lt. Verlag	19.4.2026
Zusatzinfo	Approx. 200 p. Textbook for German language market.
Verlagsort	Wiesbaden
Sprache	englisch
Maße	148 x 210 mm
Themenwelt	Mathematik / Informatik ► Informatik
Schlagworte	Causal Explanations • Distal Information • Explainable Reinforcement Learning • Important States • Reconstructed Transition Multigraph • Reconstructed Transition Multiplex
ISBN-10	3-658-50494-3 / 3658504943
ISBN-13	978-3-658-50494-6 / 9783658504946
Zustand	Neuware