Predictive machine learning for prescriptive applications: a coupled training-validating approach

no code implementations • 22 Oct 2021 • Ebrahim Mortaz, Alexander Vinel

In this research we propose a new method for training predictive machine learning models for prescriptive applications.

BIG-bench Machine Learning Decision Making +1

Benchmarking Graph Neural Networks on Link Prediction

no code implementations • 24 Feb 2021 • Xing Wang, Alexander Vinel

In this paper, we benchmark several existing graph neural network (GNN) models on different datasets for link predictions.

Benchmarking Graph Attention +1

Cross Learning in Deep Q-Networks

no code implementations • 29 Sep 2020 • Xing Wang, Alexander Vinel

In this work, we propose a novel cross Q-learning algorithm, aim at alleviating the well-known overestimation problem in value-based reinforcement learning methods, particularly in the deep Q-networks where the overestimation is exaggerated by function approximation errors.

Q-Learning reinforcement-learning +1

Reannealing of Decaying Exploration Based On Heuristic Measure in Deep Q-Network

no code implementations • 29 Sep 2020 • Xing Wang, Alexander Vinel

Existing exploration strategies in reinforcement learning (RL) often either ignore the history or feedback of search, or are complicated to implement.

reinforcement-learning Reinforcement Learning (RL)