Strategic bidding in freight transport using deep reinforcement learning

WJA van Heeswijk - Annals of Operations Research, 2022 - Springer
This paper presents a multi-agent reinforcement learning algorithm to represent strategic
bidding behavior by carriers and shippers in freight transport markets. We investigate …

Smart containers with bidding capacity: A policy gradient algorithm for semi-cooperative learning

W van Heeswijk - … Logistics: 11th International Conference, ICCL 2020 …, 2020 - Springer
Smart modular freight containers–as propagated in the Physical Internet paradigm–are
equipped with sensors, data storage capability and intelligence that enable them to route …

Deep reinforcement learning in linear discrete action spaces

W van Heeswijk, H La Poutré - 2020 Winter Simulation …, 2020 - ieeexplore.ieee.org
Problems in operations research are typically combinatorial and high-dimensional. To a
degree, linear programs may efficiently solve such large decision problems. For stochastic …

Approximate dynamic programming with neural networks in linear discrete action spaces

W van Heeswijk, H La Poutré - arXiv preprint arXiv:1902.09855, 2019 - arxiv.org
Real-world problems of operations research are typically high-dimensional and
combinatorial. Linear programs are generally used to formulate and efficiently solve these …

[PDF][PDF] Donald Duck Holiday Game: A numerical analysis of a Game of the Goose role-playing variant

WJA van Heeswijk - Board Game Studies Journal, 2020 - sciendo.com
Abstract The 1996 Donald Duck Holiday Game is a role-playing variant of the historical
Game of the Goose, involving characters with unique attributes, event squares, and random …