- Abstract: This paper proposes a method for efficient training of Q-function for continuous-state Markov Decision Processes (MDP), such that the traces of the resulting policies satisfy a Linear Temporal Logic (LTL) property. LTL, a modal logic, can express a wide range of time-dependent logical properties including safety and liveness. We convert the LTL property into a limit deterministic Buchi automaton with which a synchronized product MDP is constructed. The control policy is then synthesised by a reinforcement learning algorithm assuming that no prior knowledge is available from the MDP. The proposed method is evaluated in a numerical study to test the quality of the generated control policy and is compared against conventional methods for policy synthesis such as MDP abstraction (Voronoi quantizer) and approximate dynamic programming (fitted value iteration).
- TL;DR: As safety is becoming a critical notion in machine learning we believe that this work can act as a foundation for a number of research directions such as safety-aware learning algorithms.