Tag
This paper presents a novel model-based reinforcement learning algorithm that leverages Bayesian methods and Linear Temporal Logic specifications for efficient policy synthesis in unknown environments, demonstrating improved sample efficiency and safety compared to traditional approaches.
This paper presents a novel framework for synthesizing finite-state controllers for Partially Observable Markov Decision Processes (POMDPs) by integrating sampling, automata learning, and model-checking. The approach provides formal guarantees for threshold-safety problems that elude existing formal synthesis tools.