machine learning

Solving multi-echelon inventory problems with heuristic-guided deep reinforcement learning and centralized control (CORS)

A technical talk on reinforcement learning for inventory control.

Solving multi-echelon inventory problems with heuristic-guided deep reinforcement learning and centralized control (JOPT)

A technical talk on reinforcement learning for inventory control.

Integration of machine learning and operations research to solve more realistic problems

An overview talk of past and current research.

Solving multi-echelon inventory problems with heuristic-guided deep reinforcement learning and centralized control

Multi-echelon inventory models aim to minimize the system-wide total cost in a multi-stage supply chain by applying a proper ordering policy to each of the stages. In a practical inventory system when backlog costs can be incurred in multiple stages, …

Dynamic ride-hailing with electric vehicles

We consider the problem of an operator controlling a fleet of electric vehicles for use in a ride-hailing service. The operator, seeking to maximize profit, must assign vehicles to requests as they arise as well as recharge and reposition vehicles in …

Solving multi-echelon inventory management problems with deep reinforcement learning (IWLS)

A technical talk on reinforcement learning for inventory control.

A prototype for the recommendation of treatment-resistant depression treatments (INFORMS)

A technical talk on a prototype for recommending treatments to patients suffering from treatment-resistant depression.

A prototype for the recommendation of treatment-resistant depression treatments (CORS)

A technical talk on a prototype for recommending treatments to patients suffering from treatment-resistant depression.

Solving multi-echelon inventory problems with deep reinforcement learning (CORS)

A technical talk on reinforcement learning for inventory control.

A branch-and-bound algorithm with machine learning for the open-shop scheduling problem (CORS)

A technical talk on a the use of machine learning to derive a new branching strategy for the open shop scheduling problem.