GAN
A neural network architecture which consists of two neural networks - a generator that creates data and a discriminator that evaluates it — trained adversarially to produce outputs that resemble real data. ...
Read-through: Probabilistic Graphical Models - Learning
Read-through: Probabilistic Graphical Models - Inference
Categorical Reparameterization with Gumbel-Softmax & Concrete Distribution
Notes on using Gumbel-Softmax & Concrete Distribution in Categorical sampling ...
Maximum Entropy Reinforcement Learning via Soft Q-learning & Soft Actor-Critic
Notes on Entropy-Regularized Reinforcement Learning via SQL & SAC ...
Read-through: Probabilistic Graphical Models - Representation
Deterministic Policy Gradients
The generalization of policy gradient theorems into deterministic case and corresponding policy gradient algorithms. ...