101. Reinforcement learning approaches for the stochastic discrete lot-sizing problem on parallel machines.
- Author
-
Felizardo, Leonardo Kanashiro, Fadda, Edoardo, Del-Moral-Hernandez, Emilio, and Brandimarte, Paolo
- Subjects
- *
REINFORCEMENT learning , *STOCHASTIC programming , *MACHINERY , *MACHINE learning - Abstract
This paper addresses the stochastic discrete lot-sizing problem on parallel machines, which is a computationally challenging problem also for relatively small instances. We propose two heuristics to deal with it by leveraging reinforcement learning. In particular, we propose a technique based on approximate value iteration around post-decision state variables and one based on multi-agent reinforcement learning. We compare these two approaches with other reinforcement learning methods and more classical solution techniques, showing their effectiveness in addressing realistic size instances. • Addressing the Stochastic Discrete Lot-Sizing Problem (SDLSP). • Open-source environment for SDLSP Reinforcement Learning (RL). • Presenting LSCMA as our multi-agent RL-based proposed method for SDLSP. • Introducing Branch and Bound ADP as another proposed method for the SDLSP. • A performance comparison via out-of-sample simulations under different conditions. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF