adaPARL: Adaptive Privacy-Aware Reinforcement Learning for Sequential-Decision Making Human-in-the-Loop Systems

no code implementations • 7 Mar 2023 • Mojtaba Taherisadr, Stelios Andrew Stavroulakis, Salma Elmalaki

On the one hand, RL methods enhance the user experience by trying to adapt to the highly dynamic nature of humans.

Decision Making Reinforcement Learning (RL)

On Scrambling Phenomena for Randomly Initialized Recurrent Networks

1 code implementation • 11 Oct 2022 • Vaggos Chatziafratis, Ioannis Panageas, Clayton Sanford, Stelios Andrew Stavroulakis

Recurrent Neural Networks (RNNs) frequently exhibit complicated dynamics, and their sensitivity to the initialization process often renders them notoriously hard to train.