Reinforcement Learning Explained. MPP

Este curso pertenece al Microsoft Professional Program for Artificial Intelligence

 

Índice

Welcome 

  • Introduction
  • Applications of Reinforcement Learning
  • Overview of Modules and Labs
  • Pre-course Survey

Module 1:  Introduction to Reinforcement Learning

  • What is Reinforcement Learning
  • Comparisons
  • Elements of RL
  • Lab: Introduction to Reinforcement Learning
  • Knowledge Checks

Module 2:  Bandits

  • Bandits Framework
  • Regret Minimization
  • Bridge to Reinforcement Learning
  • Lab: Bandits
  • Knowledge Checks

Module 3:  The Reinforcement Learning Problem

  • Agent and Environment Interface
  • Markov Decision Process
  • Lab: The Reinforcement Learning Problem
  • Knowledge Checks

Module 4:  Dynamic Programming

  • Basics of Dynamic Programming
  • DP Observations
  • Lab: Dynamic Programming
  • Knowledge Checks

Module 5: Temporal Difference Learning

  • Policy Evaluation
  • Policy Optimization
  • Lab: Temporal Difference Learning
  • Knowledge Checks

Module 6: Function Approximation

  • Why Use Function Approximation
  • Linear Function Approximation
  • Lab: Q-Learning with Linear Function Approximator
  • RL with Deep Neural Networks
  • Lab: Deep Q-Learning
  • Extensions to Deep Q-Learning
  • Knowledge Checks

Module 7 Policy Gradient and Actor Critic

  • Introduction to Policy Optimization
  • Likelihood Ratio Methods
  • Lab:  REINFORCE
  • Variance Reduction
  • Lab: Baselined REINFORCE
  • Actor Critic
  • Lab: Actor Critic
  • Knowledge Checks

Post-Course Survey

  • Post-Course Survey

Get Microsoft Course Completion Certificate

  • Instructions

         

        Soporte

        Curso con soporte individualizado según se indica en https://nanfor.com/pages/soporte-2-0 

         

        * Todas las tarifas son bonificables menos el examen solo.

          €295.00