About Time: Model-free Reinforcement Learning with Timed Reward Machines

This paper introduces a model-free reinforcement learning approach that incorporates timed reward machines to handle temporal properties in complex environments. By explicitly integrating timing constraints into the reward structure, the system can learn optimal policies for tasks requiring precise temporal sequencing, which is crucial for applications in robotics, automated control systems, and process optimization where adherence to specific timeframes is essential for successful operation.