Code

Deep Reinforcement Learning teaching codes

• These codes are used for my teaching courses on Deep Reinforcement Learning. The codes are minimal implementations, intended for teaching, and available here. The codes include:
  • Basic methods and examples to understand MDPs.
  • Classic RL methods, including iterative methods, model-free tabular methods and linear approximations.
  • Model-free DRL methods: DDQN, VPG, A2C, TRPO, DDPG.
  • Model-based DRL methods: AlphaZero.

Deep Generative Models teaching codes

• These codes are used for my teaching courses on Deep Generative Models. The codes are minimal implementations, intended for teaching, and available here. The codes include:
  • Simple models, intended to understand the basic principles underlying a Generative Model, as well as classical methods used for sampling.
  • DGM models: VAE, GAN.

Random Signals teaching codes

• These codes are used in my teaching on Random Signals. The codes are explained in Spanish, and are available here.

Federated baselines

• This code contains several baselines to be used for federated learning problems, including ADMM and BNN implementations. The code is available here.