Ronny Luss

Beyond Backprop: Alternating Minimization with co-Activation Memory.

2018 · arXiv (Cornell University)

Despite significant recent advances in deep neural networks, training them remains a challenge due to the highly non-convex nature of the objective function. State-of-the-art methods rely on error backpropagation, which suffers from several well-known issues, …

Local Explanations for Reinforcement Learning

2023 · Proceedings of the AAAI Conference on Artificial Intelligence

Many works in explainable AI have focused on explaining black-box classification models. Explaining deep reinforcement learning (RL) policies in a manner that could be understood by domain users has received much less attention. In this …