Reinforcement Learning is a subfield of Machine Learning, but is also a general purpose formalism for automated decision-making and AI. This course introduces you to statistical learning techniques where an agent explicitly takes actions and interacts with the world. Understanding the importance and challenges of learning agents that make decisions is of vital importance today, with more and more companies interested in interactive agents and intelligent decision-making.
Ce cours fait partie de la Spécialisation Apprentissage par renforcement
Fundamentals of Reinforcement Learning
Offert par
Université de l'Alberta
Alberta Machine Intelligence Institute
À propos de ce cours
172,433 consultations récentes
Ce que vous allez apprendre
Formalize problems as Markov Decision Processes
Understand basic exploration methods and the exploration / exploitation tradeoff
Understand value functions, as a general-purpose tool for optimal decision-making
Know how to implement dynamic programming as an efficient solution approach to an industrial control problem
Compétences que vous acquerrez
Artificial Intelligence (AI)Machine LearningReinforcement LearningFunction ApproximationIntelligent Systems
100 % en ligne
Commencez dès maintenant et apprenez aux horaires qui vous conviennent.
Cours 1 sur 4 dans le
Dates limites flexibles
Réinitialisez les dates limites selon votre disponibilité.
Niveau intermédiaire
Probabilities & Expectations, basic linear algebra, basic calculus, Python 3.0 (at least 1 year), implementing algorithms from pseudocode.
Approx. 19 heures pour terminer
Recommandé : 4-6 hours/week
Anglais
Sous-titres : Anglais
Programme du cours : ce que vous apprendrez dans ce cours
1 heure pour terminer
Welcome to the Course!
Welcome to: Fundamentals of Reinforcement Learning, the first course in a four-part specialization on Reinforcement Learning brought to you by the University of Alberta, Onlea, and Coursera. In this pre-course module, you'll be introduced to your instructors, get a flavour of what the course has in store for you, and be given an in-depth roadmap to help make your journey through this specialization as smooth as possible.
1 heure pour terminer
4 vidéos (Total 20 min), 2 lectures
4 vidéos
Course Introduction5 min
Meet your instructors!8 min
Your Specialization Roadmap3 min
2 lectures
Reinforcement Learning Textbook10 min
Read Me: Pre-requisites and Learning Objectives10 min
7 heures pour terminer
The K-Armed Bandit Problem
For the first week of this course, you will learn how to understand the exploration-exploitation trade-off in sequential decision-making, implement incremental algorithms for estimating action-values, and compare the strengths and weaknesses to different algorithms for exploration. For this week’s graded assessment, you will implement and test an epsilon-greedy agent.
7 heures pour terminer
8 vidéos (Total 46 min), 3 lectures, 2 quiz
8 vidéos
Learning Action Values4 min
Estimating Action Values Incrementally5 min
What is the trade-off?7 min
Optimistic Initial Values6 min
Upper-Confidence Bound (UCB) Action Selection5 min
Jonathan Langford: Contextual Bandits for Real World Reinforcement Learning8 min
Week 1 Summary3 min
3 lectures
Module 2 Learning Objectives10 min
Weekly Reading30 min
Chapter Summary30 min
1 exercice pour s'entraîner
Exploration/Exploitation45 min
3 heures pour terminer
Markov Decision Processes
When you’re presented with a problem in industry, the first and most important step is to translate that problem into a Markov Decision Process (MDP). The quality of your solution depends heavily on how well you do this translation. This week, you will learn the definition of MDPs, you will understand goal-directed behavior and how this can be obtained from maximizing scalar rewards, and you will also understand the difference between episodic and continuing tasks. For this week’s graded assessment, you will create three example tasks of your own that fit into the MDP framework.
3 heures pour terminer
7 vidéos (Total 36 min), 2 lectures, 2 quiz
7 vidéos
Examples of MDPs4 min
The Goal of Reinforcement Learning3 min
Michael Littman: The Reward Hypothesis12 min
Continuing Tasks5 min
Examples of Episodic and Continuing Tasks3 min
Week 2 Summary1 min
2 lectures
Module 3 Learning Objectives10 min
Weekly Reading30 min
1 exercice pour s'entraîner
MDPs45 min
3 heures pour terminer
Value Functions & Bellman Equations
Once the problem is formulated as an MDP, finding the optimal policy is more efficient when using value functions. This week, you will learn the definition of policies and value functions, as well as Bellman equations, which is the key technology that all of our algorithms will use.
3 heures pour terminer
9 vidéos (Total 56 min), 3 lectures, 2 quiz
9 vidéos
Specifying Policies4 min
Value Functions6 min
Rich Sutton and Andy Barto: A brief History of RL7 min
Bellman Equation Derivation6 min
Why Bellman Equations?5 min
Optimal Policies7 min
Optimal Value Functions5 min
Using Optimal Value Functions to Get Optimal Policies8 min
Week 3 Summary4 min
3 lectures
Module 4 Learning Objectives10 min
Weekly Reading30 min
Chapter Summary13 min
2 exercices pour s'entraîner
Value Functions and Bellman Equations45 min
Value Functions and Bellman Equations45 min
7 heures pour terminer
Dynamic Programming
This week, you will learn how to compute value functions and optimal policies, assuming you have the MDP model. You will implement dynamic programming to compute value functions and optimal policies and understand the utility of dynamic programming for industrial applications and problems. Further, you will learn about Generalized Policy Iteration as a common template for constructing algorithms that maximize reward. For this week’s graded assessment, you will implement an efficient dynamic programming agent in a simulated industrial control problem.
7 heures pour terminer
10 vidéos (Total 72 min), 3 lectures, 2 quiz
10 vidéos
Iterative Policy Evaluation8 min
Policy Improvement4 min
Policy Iteration8 min
Flexibility of the Policy Iteration Framework4 min
Efficiency of Dynamic Programming5 min
Warren Powell: Approximate Dynamic Programming for Fleet Management (Short)7 min
Warren Powell: Approximate Dynamic Programming for Fleet Management (Long)21 min
Week 4 Summary2 min
Congratulations!3 min
3 lectures
Module 5 Learning Objectives10 min
Weekly Reading30 min
Chapter Summary30 min
1 exercice pour s'entraîner
Dynamic Programming45 min
Avis
4.8
Meilleurs avis pour FUNDAMENTALS OF REINFORCEMENT LEARNING
par PVNov 9, 2019
I understood all the necessary concepts of RL. I've been working on RL for some time now, but thanks to this course, now I have more basic knowledge about RL and can't wait to watch other courses
par ABSep 6, 2019
Concepts are bit hard, but it is nice if you undersand it well, espically the bellman and dynamic programming.\n\nSometimes, visualizing the problem is hard, so need to thoroghly get prepared.
par RDOct 15, 2019
An excellent introduction to the subject of Reinforcement Learning, accompanied by a very clear text book. The python assignments in Jupyter notebooks are both informative and helpful.
par HSSep 19, 2019
One of the best courses I finished on Coursera, I really like the structure of the course. Textbook is also provided which really helps. Looking forward to next course in the series.
par HCFeb 18, 2020
Excellent and well done course on some of the basics of RL. Good mix of lectures, reading, quizzes and programming assignments. Also a good balance between pure theory and examples.
par NSJan 1, 2020
Very well designed, it is clear that a lot of thought was put into the course. Also, I really liked the clarity regarding the learning objectives and the emphasis on understanding.
par SKDec 9, 2019
A great introduction to RL. Credit goes to the instructors Mr and Mrs white for keep in it as simple as possible. Understanding the math behind RL is the key for the RL adventure.
par NSAug 3, 2019
The ideal course to go with the book Reinforcement Learning: An Introduction. The quizzes and coding workshops are pitched just right in my opinion, neither too easy nor too hard.
À propos de Université de l'Alberta
UAlberta is considered among the world’s leading public research- and teaching-intensive universities. As one of Canada’s top universities, we’re known for excellence across the humanities, sciences, creative arts, business, engineering and health sciences.
À propos de Alberta Machine Intelligence Institute
The Alberta Machine Intelligence Institute (Amii) is home to some of the world’s top talent in machine intelligence. We’re an Alberta-based
research institute that pushes the bounds of academic knowledge and guides business understanding of artificial intelligence and machine learning.
À propos du Spécialisation Apprentissage par renforcement
The Reinforcement Learning Specialization consists of 4 courses exploring the power of adaptive learning systems and artificial intelligence (AI).
Harnessing the full potential of artificial intelligence requires adaptive learning systems. Learn how Reinforcement Learning (RL) solutions help solve real-world problems through trial-and-error interaction by implementing a complete RL solution from beginning to end.
By the end of this Specialization, learners will understand the foundations of much of modern probabilistic artificial intelligence (AI) and be prepared to take more advanced courses or to apply AI tools and ideas to real-world problems. This content will focus on “small-scale” problems in order to understand the foundations of Reinforcement Learning, as taught by world-renowned experts at the University of Alberta, Faculty of Science.
The tools learned in this Specialization can be applied to game development (AI), customer interaction (how a website interacts with customers), smart assistants, recommender systems, supply chain, industrial control, finance, oil & gas pipelines, industrial control systems, and more.
Foire Aux Questions
Quand aurai-je accès aux vidéos de cours et aux devoirs ?
Une fois que vous êtes inscrit(e) pour un Certificat, vous pouvez accéder à toutes les vidéos de cours, et à tous les quiz et exercices de programmation (le cas échéant). Vous pouvez soumettre des devoirs à examiner par vos pairs et en examiner vous-même uniquement après le début de votre session. Si vous préférez explorer le cours sans l'acheter, vous ne serez peut-être pas en mesure d'accéder à certains devoirs.
À quoi ai-je droit si je m'abonne à cette Spécialisation ?
Lorsque vous vous inscrivez au cours, vous bénéficiez d'un accès à tous les cours de la Spécialisation, et vous obtenez un Certificat lorsque vous avez réussi. Votre Certificat électronique est alors ajouté à votre page Accomplissements. À partir de cette page, vous pouvez imprimer votre Certificat ou l'ajouter à votre profil LinkedIn. Si vous souhaitez seulement lire et visualiser le contenu du cours, vous pouvez accéder gratuitement au cours en tant qu'auditeur libre.
Quelle est la politique de remboursement ?
Une aide financière est-elle possible ?
D'autres questions ? Visitez le Centre d'Aide pour les Etudiants.