-
Learning with Opponent-Learning Awareness
https://arxiv.org/abs/1709.04326 -
A DARPA Perspective on Artificial Intelligence
-
Hindsight Experience Replay (how can we be bad teachers) - Two Minute Papers
-
Latent Space Human Face Synthesis - Two Minute Papers
-
Équilibre de Nash -> problème courant des GANs
https://fr.wikipedia.org/wiki/Équilibre_de_Nash Unsupervised learning
unsupervised-learning-
Generative adversarial network
https://en.wikipedia.org/wiki/Generative_adversarial_network
-
-
Apprentissage Artificiel, Concepts et algorithmes - 2nd ed, Cornuéjols & Miclet