Login / Signup
Reward shaping to improve the performance of deep reinforcement learning in perishable inventory management.
Bram J. De Moor
Joren Gijsbrechts
Robert N. Boute
Published in:
Eur. J. Oper. Res. (2022)
Keyphrases
</>
inventory management
reinforcement learning
reward shaping
reinforcement learning algorithms
supply chain
lost sales
function approximation
complex domains
vehicle routing
optimal policy
machine learning
evolutionary algorithm
linear programming
supply chain management
action selection