5 citations · 10 across the 8 of their papers we have counts for
5 papers · 1 filter
Machine Learning Predictions for Traffic Equilibria in Road Renovation Scheduling
Robbert Bosch, Wouter van Heeswijk, Patricia Rogetzer +1
Accurately estimating the impact of road maintenance schedules on traffic conditions is important because maintenance operations can substantially worsen congestion if not carefull…
Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces
Fabian Akkerman, Julius Luy, Wouter van Heeswijk +1
Large discrete action spaces (LDAS) remain a central challenge in reinforcement learning. Existing solution approaches can handle unstructured LDAS with up to a few million actions…
Natural Policy Gradients In Reinforcement Learning Explained
W. J. A. van Heeswijk
Traditional policy gradient methods are fundamentally flawed. Natural gradients converge quicker and better, forming the foundation of contemporary Reinforcement Learning such as T…
A Gentle Lecture Note on Filtrations in Reinforcement Learning
W. J. A. van Heeswijk
This note aims to provide a basic intuition on the concept of filtrations as used in the context of reinforcement learning (RL). Filtrations are often used to formally define RL pr…
Approximate Dynamic Programming with Neural Networks in Linear Discrete Action Spaces
Wouter van Heeswijk, Han La Poutré
Real-world problems of operations research are typically high-dimensional and combinatorial. Linear programs are generally used to formulate and efficiently solve these large decis…