Inventory Replenishment and Fulfillment Decisions for an Omnichannel Retailer: A Decomposition-Based Reinforcement Learning Method

Wednesday 14 May 2025, 1:00pm to 2:00pm

Venue

LT3 Lancaster University Management School, Lancaster - View Map

Open to

Postgraduates, Public, Staff

Registration

Registration not required - just turn up

Event Details

Mary Kolyaei, PhD candidate from University of Melbourne, will present a seminar to the Management Science Department.

Abstract: We address the replenishment and fulfilment challenges faced by an omnichannel retailer within a capacitated retail network, selling products to a large region across

a multi-period horizon. This horizon is partitioned into cycles, where replenishment occurs at the start of each cycle and fulfilment decisions regarding how much to allocate across sales channels take place in each time period. The problem is formulated as a Markov Decision Process (MDP). To solve the MDP, we propose decomposition-based reinforcement learning methods. Our results reveal that the proposed approach effectively handles high-dimensional, large-scale decision while improving profitability compared to baseline methods.

Speaker

Mary Kolyaei

University of Melbourne

Contact Details

Name Gay Bentinck
Email

g.bentinck@lancaster.ac.uk

Directions to LT3 Lancaster University Management School

Lecture Theatre 3 in the Management School