activity
20182022
most citedA State Aggregation Approach for Solving Knapsack Problem with Deep Reinforcement Learning

14 citations · 18 across the 4 of their papers we have counts for

collaborators

7 papers

cs.AI20221 cited

The First AI4TSP Competition: Learning to Solve Stochastic Routing Problems

Laurens Bliek, Paulo da Costa, Reza Refaei Afshar +19

This paper reports on the first international competition on AI for the traveling salesman problem (TSP) at the International Joint Conference on Artificial Intelligence 2021 (IJCA…

cs.NE202014 cited

A State Aggregation Approach for Solving Knapsack Problem with Deep Reinforcement Learning

Reza Refaei Afshar, Yingqian Zhang, Murat Firat +1

This paper proposes a Deep Reinforcement Learning (DRL) approach for solving knapsack problem. The proposed method consists of a state aggregation step based on tabular reinforceme…

stat.ML20202 cited

Algorithms for slate bandits with non-separable reward functions

Jason Rhuggenaath, Alp Akcay, Yingqian Zhang +1

In this paper, we study a slate bandit problem where the function that determines the slate-level reward is non-separable: the optimal value of the function cannot be determined by…

cs.LG2020

Learning 2-opt Heuristics for the Traveling Salesman Problem via Deep Reinforcement Learning

Paulo R. de O. da Costa, Jason Rhuggenaath, Yingqian Zhang +1

Recent works using deep learning to solve the Traveling Salesman Problem (TSP) have focused on learning construction heuristics. Such approaches find TSP solutions of good quality…

cs.NE20191 cited

Machine Learning based Simulation Optimisation for Trailer Management

Dylan Rijnen, Jason Rhuggenaath, Paulo R. de O. da Costa +1

In many situations, simulation models are developed to handle complex real-world business optimisation problems. For example, a discrete-event simulation model is used to simulate…

cs.LG2019

Remaining Useful Lifetime Prediction via Deep Domain Adaptation

Paulo R. de O. da Costa, Alp Akcay, Yingqian Zhang +1

In Prognostics and Health Management (PHM) sufficient prior observed degradation data is usually critical for Remaining Useful Lifetime (RUL) prediction. Most previous data-driven…