LeDeepChef 👨🏻‍🍳 : Deep Reinforcement Learning Agent for Families of Text-Based Games

AAAI 2020

While Reinforcement Learning (RL) approaches lead to significant achievements in a variety of areas in recent history, natural …

Ellipsoidal Trust Region Methods and the Marginal Value of Hessian Information for Neural Network Training

NeurIPS 2019 Workshop: Beyond First-Order Methods in ML

We investigate the use of ellipsoidal trust region constraints for second-order …

Local Saddle Point Optimization: A Curvature Exploitation Approach


Gradient-based optimization methods are the most popular choice for finding local optima for classical minimization and …