Reinforcement learning (RL) is a machine learning method in which a model optimizes its decision-making strategy based on rewards or penalties received for the actions it takes in an environment, often simulated. An example of an optimized process could be work scheduling in a restaurant, with the cost function being the absolute error of the difference between the scheduled and actual delivery times of an order. In task planning, RL stands out for its ability to handle problems requiring a complex sequence of actions, where traditional planning algorithms may struggle. RL models can effectively explore the solution space, adjusting their decisions to changing conditions, which enables dynamic and adaptive task execution management. RL is a broad class encompassing various approaches to achieving a goal, and in this research, we focus on selected ones. Three popular RL methods named DQN, SARSA and TD-AC have been implemented and evaluated. The study was conducted in a simulated environment designed to replicate a "delivery-based" restaurant business model. The kitchen simulation model has been developed based on 65,845 recorded food preparation processes performed in 30 restaurants located throughout Poland. A rule-based, queue-driven model (FIFO) served as the baseline for absolute quality comparison of the generated schedules. The results show that, for the defined problem, the quality of the scheduling outcomes varies significantly depending on the choice of learning algorithm. Notably, the hybrid approach performed best under simulation conditions, considerably reducing the total completion time in a scenario reflecting the operations of a small, typical restaurant.
References
[1] Deguchi A. et al.: What is society 5.0. Society 5.0, 2020, 1–24.
[2] Dziurzanski P., Zhao S., Indrusiak L. S.: Integrated Process Planning and Scheduling in Commercial Smart Kitchens. arXiv preprint arXiv:1910.03322, 2019.
[3] Dziurzanski P., Kabala K., Konrad A.: A stochastic interval algebra for smart factory process. Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska – IAPGOS 1, 2025, 33–38.
[4] Hamada R., et al.: Cooking navi: assistant for daily cooking in kitchen. 13th annual ACM international conference on Multimedia. 2005.
[5] Kiesel J.: The internet of things in restaurants. 2018 [https://www.manufacturingtomorrow.com/article/2017/03/the-internet-of-things-in-restaurants/9261].
[6] Lei J., Ren X., Fox D.: Fine-grained kitchen activity recognition using rgb-d. ACM Conference on Ubiquitous Computing. 2012.
[7] Mizrahi M., et al.: Digital gastronomy: Methods & recipes for hybrid cooking. 29th Annual Symposium on User Interface Software and Technology. 2016.
[8] Mohan A., Zhang A., Lindauer M.: Structure in Deep Reinforcement Learning: A Survey and Open Problems. Journal of Artificial Intelligence Research 79, 2024, 1167–1236.
[9] Moritz P., et al.: Ray: A distributed framework for emerging {AI} applications. 13th USENIX symposium on operating systems design and implementation –OSDI 18. 2018.
[10] Padakandla S.: A survey of reinforcement learning algorithms for dynamically varying environments. ACM Computing Surveys – CSUR 54(6), 2021, 1–25.
[11] Sutton R. S., Barto A. G.: Reinforcement learning: An introduction. MIT press, 2018.
[12] Ustundag A., Cevikcan E.: Industry 4.0: managing the digital transformation. Springer, 2017.
[13] Van Hasselt H., Guez A., Silver D.: Deep reinforcement learning with double q-learning. AAAI conference on artificial intelligence 30(1), 2016.
[14] Iterative.ai. Data Version Control (DVC). Iterative.ai, 2025 [http://dvc.org] (accessed: 21.08.2025).
[15] MLflow Project (part of LF Projects, LLC). MLflow. MLflow Project, 2025 [http://mlflow.org] (accessed: 21.08.2025).
[16] Project Jupyter. Project Jupyter. Project Jupyter, 2025 [http://jupyter.org] (accessed: 21.08.2025).
[17] PyTorch Foundation. PyTorch. PyTorch Foundation, 2025 [http://pytorch.org] (accessed: 21.08.2025).
[18] Rynek wewnętrzny w 2022 r., Analizy statystyczne. Główny Urząd Statystyczny. 2023.