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.
提供:
このコースについて
Probabilities & Expectations, basic linear algebra, basic calculus, Python 3.0 (at least 1 year), implementing algorithms from pseudocode
習得するスキル
- Artificial Intelligence (AI)
- Machine Learning
- Reinforcement Learning
- Function Approximation
- Intelligent Systems
Probabilities & Expectations, basic linear algebra, basic calculus, Python 3.0 (at least 1 year), implementing algorithms from pseudocode
提供:

アルバータ大学(University of 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.

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
シラバス - 本コースの学習内容
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.
レビュー
- 5 stars81.86%
- 4 stars13.82%
- 3 stars2.74%
- 2 stars0.64%
- 1 star0.91%
SAMPLE-BASED LEARNING METHODS からの人気レビュー
Everything is great overall but It would be more better if DynaQ & DynaQ+ were explained more detail in the lecture instead of assignment.
It's an important course in understanding the working of reinforcement learning. Although some important and complex topics are not explored in this course which are mentioned in the textbook.
Good balance of theory and programming assignments. I really like the weekly bonus videos with professors and developers. Recommend to everyone.
Overall a very nice course, well explained and presented. Sometimes, it would be nice to see the slides 'full screen' rather than the small version in the corner.
強化学習専門講座について
The Reinforcement Learning Specialization consists of 4 courses exploring the power of adaptive learning systems and artificial intelligence (AI).

よくある質問
いつ講座や課題にアクセスできるようになりますか?
この専門講座をサブスクライブすると何を行うことができるようになりますか?
学資援助はありますか?
さらに質問がある場合は、受講者ヘルプセンターにアクセスしてください。