Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

University of Alberta

Sample-based Learning Methods

University of Alberta and Alberta Machine Intelligence Institute via Coursera


In this course, you will learn about several algorithms that can learn near optimal policies based on trial and error interaction with the environment---learning from the agent’s own experience. Learning from actual experience is striking because it requires no prior knowledge of the environment’s dynamics, yet can still attain optimal behavior. We will cover intuitively simple but powerful Monte Carlo methods, and temporal difference learning methods including Q-learning. We will wrap up this course investigating how we can get the best of both worlds: algorithms that can combine model-based planning (similar to dynamic programming) and temporal difference updates to radically accelerate learning.

By the end of this course you will be able to:

- Understand Temporal-Difference learning and Monte Carlo as two strategies for estimating value functions from sampled experience
- Understand the importance of exploration, when using sampled experience rather than dynamic programming sweeps within a model
- Understand the connections between Monte Carlo and Dynamic Programming and TD.
- Implement and apply the TD algorithm, for estimating value functions
- Implement and apply Expected Sarsa and Q-learning (two TD methods for control)
- Understand the difference between on-policy and off-policy control
- Understand planning with simulated experience (as opposed to classic planning strategies)
- Implement a model-based approach to RL, called Dyna, which uses simulated experience
- Conduct an empirical study to see the improvements in sample efficiency when using Dyna


  • Welcome to the Course!
    • Welcome to the second course in the Reinforcement Learning Specialization: Sample-Based Learning Methods, brought to you by the University of Alberta, Onlea, and Coursera. In this pre-course module, you'll be introduced to your instructors, and get a flavour of what the course has in store for you. Make sure to introduce yourself to your classmates in the "Meet and Greet" section!
  • Monte Carlo Methods for Prediction & Control
    • This week you will learn how to estimate value functions and optimal policies, using only sampled experience from the environment. This module represents our first step toward incremental learning methods that learn from the agent’s own interaction with the world, rather than a model of the world. You will learn about on-policy and off-policy methods for prediction and control, using Monte Carlo methods---methods that use sampled returns. You will also be reintroduced to the exploration problem, but more generally in RL, beyond bandits.
  • Temporal Difference Learning Methods for Prediction
    • This week, you will learn about one of the most fundamental concepts in reinforcement learning: temporal difference (TD) learning. TD learning combines some of the features of both Monte Carlo and Dynamic Programming (DP) methods. TD methods are similar to Monte Carlo methods in that they can learn from the agent’s interaction with the world, and do not require knowledge of the model. TD methods are similar to DP methods in that they bootstrap, and thus can learn online---no waiting until the end of an episode. You will see how TD can learn more efficiently than Monte Carlo, due to bootstrapping. For this module, we first focus on TD for prediction, and discuss TD for control in the next module. This week, you will implement TD to estimate the value function for a fixed policy, in a simulated domain.
  • Temporal Difference Learning Methods for Control
    • This week, you will learn about using temporal difference learning for control, as a generalized policy iteration strategy. You will see three different algorithms based on bootstrapping and Bellman equations for control: Sarsa, Q-learning and Expected Sarsa. You will see some of the differences between the methods for on-policy and off-policy control, and that Expected Sarsa is a unified algorithm for both. You will implement Expected Sarsa and Q-learning, on Cliff World.
  • Planning, Learning & Acting
    • Up until now, you might think that learning with and without a model are two distinct, and in some ways, competing strategies: planning with Dynamic Programming verses sample-based learning via TD methods. This week we unify these two strategies with the Dyna architecture. You will learn how to estimate the model from data and then use this model to generate hypothetical experience (a bit like dreaming) to dramatically improve sample efficiency compared to sample-based methods like Q-learning. In addition, you will learn how to design learning systems that are robust to inaccurate models.

Taught by

Martha White and Adam White

Related Courses


4.6 rating, based on 35 reviews

Start your review of Sample-based Learning Methods

  • Anonymous
    This is somewhat enjoyable class, but could be much, much better. First, as other people noted, the programming content is not ideal. The course would have benefited from including an introduction to RLGlue and also if possible, a brief survey of Python/R...
  • Profile image for Stewart Adamson
    Stewart Adamson

    Stewart Adamson completed this course, spending 5 hours a week on it and found the course difficulty to be medium.

    To be brief, this is a great course on Reinforcement Learning (RL) and I thoroughly recommend it. This is the second course in the four course Reinforcement Learning specialization from the Alberta Machine Intelligence Institute (AMII) at University of...
  • Anonymous
    It is very comprehensive course based on Sutton's book. Programming exercises are good and interesting, with a lot of visualisations (based on examples from the book).

    The subject is complex and my advice would be to put some notes from generalisation and summary chapters at the beginning in order to have better anticipation of the course.

    There were some animations that was extremely helpful for understanding. This not at all easy topic to teach.
  • Anonymous

    Anonymous completed this course.

    Overall the course seem to me very well structured and the videous help you to understand the book content. The only drawback for which I gave only 4 stars out of 5 is the submission limit of programming assignments. You can submit the assignment only 5 times afterwards you are blocked for 4 months. This does not feel right, you should be able to submit it as many times as you need, until you are successful, since you pay for the course. Only in this way you would be encouraged to think at more and more possible solutions
  • Anonymous
    I really have been enjoying the classes in this specialization. I have had the Sutton and Barto book for years but was never as engaged with learning the material as I have been with this class. I find the videos insightful and the programming exercises really make you think through the equations/algorithms
  • Anonymous
    Great course. The explanations are to the point, the exercises take care of the irrelevant code and only let you do the important stuff. And I like the guest lectures that are sprinkled throughout this specialization!
  • Anonymous
    The course is carefully organised and really pedagogical. The programming assignments is also well designed and it is really interesting to see how the algorithms works in practice.
  • Anonymous
    The readings and videos are very informative and are easy to learn from. However, the quizzes and programming assignments can be a pain sometimes.
  • Anonymous
    This course is absolutely worth the time and effort. The instructors are really great and the programming assignments help a lot.
  • Anonymous

    Anonymous completed this course.

    1) Material is highly relevant
    2) Programming assignments are unmanageable - even though you manage to create code that passes unit tests, the grader that attempts to evaluate graphs generated during experiments works as black magic, and if your submission is rejected - you'll never know why
    3) regarding the lectures - personally for me they can be replaced by reading relevant chapters of RL book
  • Anonymous

    Anonymous completed this course.

    The course is fairly well detailed and contains a good deal of topics. If I have any complaints, it would be that the lectures could be a bit longer and dive into topics a little more. To be fair to the course, they do give you a weekly reading list from...
  • Anonymous
    The subject matter is fully fledged and lays a strong foundation in holistic nature. The organization of the course is thought through and that makes the learner to have a clean understanding with less confusions. This course has materials from assignments and quizzes to discussions and videos from industrial experts, everything is perfectly linked and that makes it very interesting to explore. Thank you very much for this course. I loved every minute of this and looking forward to the rest of the courses in the RL specialization. Thank you.
  • Anonymous
    Enjoyed the course, really getting a sense of the breadth of the field and the potential applications, and enough knowledge to start using in the real world.

    In my opinion the programming assignments were useful, and struck a good balance of making you think about how to implement the key concepts, without having to waste a lot of time programming all the other stuff. Found them really helpful in cementing my understanding of the material.

    Enjoyed it enough, that I plan to finish the specialization.

  • Anonymous
    Great pointers to the reading materials, amazing animations in the short (but still enough)videos so that you can verify your understanding from the read content.

    Assignments are fast to work on and at the same time they give you complete gist of the implementation that you work on. They have already coded the testing and visualization part and they only expect you to understand the algorithm so that you parts fill the important empty functions of the algorithm.

  • Anonymous
    This course complements the most in-depth introduction to Reinforcement Learning, the book by Barto and Sutton.

    It was exactly what I needed to understand the corresponding part of the book properly.

    You learn to implement RL agents with different algorithms. Covers relevant parts of chapters 5 to 8. Highly recommended!
  • Profile image for Ravi Shankar
    Ravi Shankar
    The course content and the instructors are great. I really enjoyed the programming assignments and quizzes. Also, the lectures from the different people from industrial sectors and engineering help bridge the gap between the theory and the practical application of these RL methods.
  • Anonymous
    Wish there was extension courses for more methods mentioned in the book

    Some of the videos seem to rush over details which can make it difficult to read details on slides. Leave the slides up longer and make the inset larger. Nevertheless very interesting material.
  • Anonymous
    Really nice course. Loved the exercises and the explanations. It is true that the videos are short, but they serve as a complement to the book, and in that sense, they are perfect.
  • Profile image for Luis Alaniz
    Luis Alaniz
    Excellent course and teachers. You learn from the ground up reinforcement learning using sampling methods for discrete finite dimensional problems.
  • Anonymous
    Very good course. The course creators took very good care of curating the material and assignments in order to maximise the learning experience!

Never Stop Learning!

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free