Chevron Left
返回到 Sample-based Learning Methods

學生對 阿尔伯塔大学 提供的 Sample-based Learning Methods 的評價和反饋

920 個評分
189 條評論


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...



Great course, giving it 5 stars though it deserves both because the assignments have some serious issues that shouldn't actually be a matter. All the other parts are amazing though. Good job


Really great resource to follow along the RL Book. IMP Suggestion: Do not skip the reading assignments, they are really helpful and following the videos and assignments becomes easy.


26 - Sample-based Learning Methods 的 50 個評論(共 185 個)

創建者 Damian K


Great balance between theory and demonstration of how all techniques works. Exercises are prepared so it is possible to focus on core part of concepts. And if you will you can take deep dive into exercise and how experiments are designed. Very recommended course.

創建者 Yoel S


Interesting topic, medium-advanced material, loved the programming assignments (despite technical difficulties with submissions), the textbook is excellent, and the online course is well organized, balanced, and well presented. Thank you to the whole team!

創建者 İbrahim Y


The course dives into the methods that are important for basic knowledge of RL intuition. Well designed examples and assignments. It seems somehow easy if a learner knows sth in advance, however, for a new learner of RL, this course is highly recommended.

創建者 Majd W


One of the amazing things this specialization stands out in is that it is based on a textbook. if you read from it and watch the lectures, you will have a very good understanding of the material. Also, the programming assignments are very beneficial.

創建者 Jesse W


This is an excellent course in reinforcement learning. They provide a PDF for a textbook which is very clear and readable, and the lectures do a great job at reinforcing the concepts. The programming assignments are pretty interesting as well.

創建者 AhmadrezaSheibanirad


This course doesn't cover all concept of Sutton book. like n-step TD (chapter7) or some Planning and Learning with Tabular Methods (8-5, 8-6, 8-7, 8-8, 8-9, 8-10, 8-11), but what they teach you and cover are so practical, complete and clear.

創建者 Luis G


Great course!!! Even better than the 1st one. I tried to read the book before taking the course, and some algorithmics have not been clear to me until I saw the videos (DynaQ, DynaQ+). Same wrt some key concepts (on vs off policy learning).

創建者 D. R


Course is not easy, videos presentation is a bit dull - but the material is cool and interesting, and the additional quizzes, videos and especially notebooks make it a great course - you learn a lot and see progress. Highly recommended.

創建者 Shashidhara K


This course required more work than the 1st in the series, (may be i took it lightly as the first was not that difficult). Request : Please include some worked examples (calculations) or include in graded/ungraded quiz, will be nice.

創建者 Aze A


The lectures videos are concise and clear. The labs offer the opportunity to put in practice the theory. Al in all very content with content and the way the material was explain. Watching the interviews with SME was very motivating.

創建者 Rafael B M


The course build up the knowledge required to fully understand the basis of Reinforcement Learning, in that way, the student become well prepared and ready to investigate broader approaches for RL such as Function Approximation.

創建者 Jose M R F


Phenomenal walk-through over Sutton & Barto's book. The programming exercises really help to dive deeper into the details of each algorithm, visualize their behavior and get dirty with the intricacies of the implementations.

創建者 Lucas O S


Awesome! It is a pitty n-steps and eligibility traces were not included - felt like a huge gap. All the future chapters have a reference to the n-steps, and your understanding won't be complete unless you learn that as well.

創建者 Daniel S P G


Excellent course that naturally extends the first specialization course. The application examples in programming are very good and I loved how RL gets closer and closer to how a living being thinks.

創建者 Dani C


The material discussed is very clear, and the graded quizzes and programming assignments force you to really understand what you have just heard. I enjoyed this course a lot, and learned even more.

創建者 george p


Well structured course with amazing mentoring and examples. Chapters of the book are easy to follow with meaningful applications. Coursework particularly interesting with high hands-on experience.

創建者 Andreas_spanopoulos


Great course, giving it 5 stars though it deserves both because the assignments have some serious issues that shouldn't actually be a matter. All the other parts are amazing though. Good job

創建者 Kinal M


Really great resource to follow along the RL Book. IMP Suggestion: Do not skip the reading assignments, they are really helpful and following the videos and assignments becomes easy.

創建者 Gordon L W C


The course is intermediate in difficulty. But it explains the concept very clearly for me to understand difference between different sample based learning methods.

創建者 Art H


Well done. Follows Reinforcement Learning (Sutton/Barto) closely and explains topics well. Graded notebooks are invaluable in understanding the material well.

創建者 Kees J d V


Reinforcement Learning has added a whole new paradigm to my thinking. The course + book combination is perfect. The instructors are extremely good :D

創建者 Karim D


Excellent course. Really well taught. Good pace of videos and assignments, with the support of perfect reading material. thank you tot he teachers.

創建者 Giulio C


Excellent course and instructors! I'm very excited about this specialization. They are able to explain hard concepts from the book in an easy way.

創建者 Umut Z


Good balance of theory and programming assignments. I really like the weekly bonus videos with professors and developers. Recommend to everyone.



One of most accurate, precise and well explained courses I have ever had with Coursera. Congratulations for teachers and course creators.