In this course, you will learn how to solve problems with large, high-dimensional, and potentially infinite state spaces. You will see that estimating value functions can be cast as a supervised learning problem---function approximation---allowing you to build agents that carefully balance generalization and discrimination in order to maximize reward. We will begin this journey by investigating how our policy evaluation or prediction methods like Monte Carlo and TD can be extended to the function approximation setting. You will learn about feature construction techniques for RL, and representation learning via neural networks and backprop. We conclude this course with a deep-dive into policy gradient methods; a way to learn policies directly without learning a value function. In this course you will solve two continuous-state control tasks and investigate the benefits of policy gradient methods in a continuous-action environment. Prerequisites: This course strongly builds on the fundamentals of Courses 1 and 2, and learners should have completed these before starting this course. Learners should also be comfortable with probabilities & expectations, basic linear algebra, basic calculus, Python 3.0 (at least 1 year), and implementing algorithms from pseudocode. By the end of this course, you will be able to: -Understand how to use supervised learning approaches to approximate value functions -Understand objectives for prediction (value estimation) under function approximation -Implement TD with function approximation (state aggregation), on an environment with an infinite state space (continuous state space) -Understand fixed basis and neural network approaches to feature construction -Implement TD with neural network function approximation in a continuous state environment -Understand new difficulties in exploration when moving to function approximation -Contrast discounted problem formulations for control versus an average reward problem formulation -Implement expected Sarsa and Q-learning with function approximation on a continuous state control task -Understand objectives for directly estimating policies (policy gradient objectives) -Implement a policy gradient method (called Actor-Critic) on a discrete state environment
提供：
習得するスキル
シラバス - 本コースの学習内容
Welcome to the Course!
Welcome to the third course in the Reinforcement Learning Specialization: Prediction and Control with Function Approximation, 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!
On-policy Prediction with Approximation
This week you will learn how to estimate a value function for a given policy, when the number of states is much larger than the memory available to the agent. You will learn how to specify a parametric form of the value function, how to specify an objective function, and how estimating gradient descent can be used to estimate values from interaction with the world.
Constructing Features for Prediction
The features used to construct the agent’s value estimates are perhaps the most crucial part of a successful learning system. In this module we discuss two basic strategies for constructing features: (1) fixed basis that form an exhaustive partition of the input, and (2) adapting the features while the agent interacts with the world via Neural Networks and Backpropagation. In this week’s graded assessment you will solve a simple but infinite state prediction task with a Neural Network and TD learning.
Control with Approximation
This week, you will see that the concepts and tools introduced in modules two and three allow straightforward extension of classic TD control methods to the function approximation setting. In particular, you will learn how to find the optimal policy in infinite-state MDPs by simply combining semi-gradient TD methods with generalized policy iteration, yielding classic control methods like Q-learning, and Sarsa. We conclude with a discussion of a new problem formulation for RL---average reward---which will undoubtedly be used in many applications of RL in the future.
Policy Gradient
Every algorithm you have learned about so far estimates a value function as an intermediate step towards the goal of finding an optimal policy. An alternative strategy is to directly learn the parameters of the policy. This week you will learn about these policy gradient methods, and their advantages over value-function based methods. You will also learn how policy gradient methods can be used to find the optimal policy in tasks with both continuous state and action spaces.
Prediction and Control with Function Approximation からの人気レビュー
Great Learning, the best part was the Actor-Critic algorithm for a small pendulum swing task all from stratch using RLGLue library. Love to learn how experimentation in RL works.
Great course. Slightly more complex than courses 1 and 2, but a huge improvement in terms of applicability to real-world situations.
講師
Martha White
Assistant Professor
Adam White
Assistant Professorアルバータ大学（University of Alberta）について
Alberta Machine Intelligence Instituteについて
強化学習専門講座について
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？
修了証に登録すると、すべてのビデオ、テスト、およびプログラミング課題（該当する場合）にアクセスできます。ピアレビュー課題は、セッションが開始してからのみ、提出およびレビューできます。購入せずにコースを検討することを選択する場合、特定の課題にアクセスすることはできません。
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？
コースに登録する際、専門講座のすべてのコースにアクセスできます。コースの完了時には修了証を取得できます。電子修了証が成果のページに追加され、そこから修了証を印刷したり、LinkedInのプロフィールに追加したりできます。コースの内容の閲覧のみを希望する場合は、無料でコースを聴講できます。
返金ポリシーについて教えてください。
学資援助はありますか？
さらに質問がある場合は、受講者向けヘルプセンターにアクセスしてください。