In online learning an algorithm plays against an environment with losses...
Deep Reinforcement Learning (DRL) has recently achieved significant adva...
Neural networks are vulnerable to small adversarial perturbations. Exist...
We propose Max-Margin Adversarial (MMA) training for directly maximizing...
Deep neural networks are known to suffer the catastrophic forgetting pro...
In this paper, we investigate Dimensionality reduction (DR) maps in an
i...
We propose a novel regularizer to improve the training of Generative
Adv...
We study the problem of identifying the best action among a set of possi...