University of Twente Student Theses


Reinforcement learning in modality planning

Stortelder, Daan (2022) Reinforcement learning in modality planning.

[img] PDF
Abstract:We researched the potential of reinforcement learning for the modality planning of a hinterland logistic service provider. The RL-method outperformed the benchmark heuristic for all problem instances, except a large problem instance with unbalanced arrival probabilities. However, we conclude that the model is able to perform general planning activities, is able to let multiple barges collaborate and can handle problem instances of realistic size with balanced arrival probabilities.
Item Type:Essay (Master)
Combi Terminal Twente, Hengelo, Netherlands
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:55 traffic technology, transport technology
Programme:Industrial Engineering and Management MSc (60029)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page