Code

Deep Reinforcement Learning Classes

Minimal implementations used for teaching in DRL courses.

• Basic methods and examples to understand MDPs.
• Classic RL: iterative methods, model-free tabular methods, linear approximations.
• Model-free DRL: DDQN, VPG, A2C, TRPO, DDPG, SAC.
• Model-based DRL: AlphaZero.

Deep Generative Models Classes

Minimal implementations used for teaching in DGM courses.

• Simple models to understand the basic principles of generative modelling and classical sampling methods.
• DGM models: VAE, GAN.

Random Signals Teaching Codes

Codes used in the Random Signals course. Explanations in Spanish.

Federated Learning Baselines

Baseline implementations for federated learning research, including ADMM and BNN.

Research publication codes

Most research outputs include reproducibility code linked directly from each publication entry.