Reward shaping to improve the performance of deep reinforcement learning in perishable inventory management

DOI10.1016/j.ejor.2021.10.045zbMath1506.90010OpenAlexW3209078210MaRDI QIDQ2140199

Joren Gijsbrechts, Bram J. De Moor, Robert N. Boute

Publication date: 20 May 2022

Published in: European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ejor.2021.10.045

zbMATH Keywords

inventorytransfer learningperishable inventory managementdeep reinforcement learningreward shaping

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Inventory, storage, reservoirs (90B05)

Related Items (3)

Cluster-based lateral transshipments for the Zambian health supply chain ⋮ Navigational guidance -- a deep learning approach ⋮ Can accessing much data reshape the theory? Inventory theory under the challenge of data-driven systems

Uses Software

• Adam
• AlphaZero

Cites Work

• Unnamed Item
• A heuristic to manage perishable inventory with batch ordering, positive lead-times, and time-varying demand
• A perishable inventory model with positive order lead times
• Blood platelet production: optimization by dynamic programming and simulation
• A Comparison Of Alternative Approximations For Ordering Perishable Inventory^*
• Optimal Ordering Policies for Perishable Inventory—II
• Optimal Ordering Policy for a Perishable Commodity with Fixed Lifetime
• Analysis of Single Critical Number Ordering Policies for Perishable Inventories
• A Markovian Model for a Perishable Product Inventory
• LIFO Inventory Systems
• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
• Some Results Concerning Optimum Inventory Policies
• Optimal Issuing Policies for Perishable Inventory
• Optimal Inventory Policy

This page was built for publication: Reward shaping to improve the performance of deep reinforcement learning in perishable inventory management