Deep and Reinforcement Learning

Deep and Reinforcement Learning

This course presents the principles of Reinforcement Learning as an artificial intelligence tool based on the interaction of the machine with its environment, with applications to control tasks (e.g. robotics, autonomous driving) o decision making. It also advances in the development of deep neural networks trained with little or no supervision, both for discriminative and generative tasks.

The course webpage can be found: [2020]

DLR Lectures (2020)

rl_2020_l1_Introduction.pdf

Lecture 1: Introduction to Reinforcement Learning

Learning Paradigms

Instructor: Josep Vidal

rl_2020_l2_MDP.pdf

Lecture 2: Markov Decission Processes and Bellman's equations

Reinforcement Learning

Instructor: Margarita Cabrera

rl_2020_l3_DP.pdf

Lecture 3: Dynamic Programming

Reinforcement Learning

Instructor: Josep Vidal

rl_2020_l4_MC.pdf

Lecture 4: Monte Carlo Methods

Reinforcement Learning

Instructor: Josep Vidal

rl_2020_l5_TD.pdf

Lecture 5: TD-Learning: SARSA and Q-learning

Reinforcement Learning

Instructor: Margarita Cabrera

rl_2020_l6_VFPG.pdf

Lecture 6: Value Function and Policy Gradient

Reinforcement Learning

Instructor: Josep Vidal

drl_2020_l1_introdeep.pdf

Lecture 7: Introduction to Deep Reinforcement Learning

Learning Paradigms

Instructor: Xavi Giró-i-Nieto

drl_2020_l3_nntrain.pdf

Lecture 8: Training Neural Networks for RL

Reinforcement Learning

Instructor: Xavi Giró-i-Nieto

drl_2020_l4_dqn.pdf

Lecture 9: Deep Q-Networks

Reinforcement Learning

Instructor: Xavi Giró-i-Nieto

drl_2020_l6_reinforce.pdf

Lecture 10: Deep Policy Gradient

Reinforcement Learning

Instructor: Xavi Giró-i-Nieto