|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/beginner-master-rl-1/
课程评论：没有评论
**课程名称：** 从入门到精通：Python中的强化学习 **课程概述：** 本课程是关于强化学习（Reinforcement Learning，RL）最全面的入门指南，让你掌握人工智能的三大范式之一。你将从零开始实现能够通过经验解决控制问题的自适应算法。此外，课程还将教授如何将这些算法与深度学习和神经网络相结合，从而进入深度强化学习（Deep Reinforcement Learning）的领域。 **课程目标：** * 搭建扎实的强化学习基础，使你能够理解新兴的算法。 * 为后续更深入的强化学习课程和其他高级算法的学习做好准备。\ * 注重实践技能的培养。 **课程内容：** 课程分为三个部分，涵盖以下主题： **第一部分：表格方法 (Tabular methods)** * 马尔可夫决策过程 (Markov decision process) * 动态规划 (Dynamic programming) * 蒙特卡洛方法 (Monte Carlo methods) * 时间差分方法 (Time difference methods)，包括 SARSA 和 Q-Learning * N步自举 (N-step bootstrapping) **第二部分：连续状态空间 (Continuous state spaces)** * 状态聚合 (State aggregation) * 瓦片编码 (Tile Coding) **第三部分：深度强化学习 (Deep Reinforcement Learning)** * 深度 SARSA (Deep SARSA) * 深度 Q-Learning (Deep Q-Learning) * REINFORCE 算法 * 优势演员-评论家 (Advantage Actor-Critic / A2C) **学习方式：** 学完每类方法最重要的概念后，将在 Jupyter Notebook 中从零开始实现一个或多个对应的算法。
This is the most complete Reinforcement Learning course on Udemy. In it you will learn the basics of Reinforcement Learning, one of the three paradigms of modern artificial intelligence. You will implement from scratch adaptive algorithms that solve control tasks based on experience. You will also learn to combine these algorithms with Deep Learning techniques and neural networks, giving rise to the branch known as Deep Reinforcement Learning.This course will give you the foundation you need to be able to understand new algorithms as they emerge. It will also prepare you for the next courses in this series, in which we will go much deeper into different branches of Reinforcement Learning and look at some of the more advanced algorithms that exist.The course is focused on developing practical skills. Therefore, after learning the most important concepts of each family of methods, we will implement one or more of their algorithms in jupyter notebooks, from scratch.This course is divided into three parts and covers the following topics:Part 1 (Tabular methods):- Markov decision process- Dynamic programming- Monte Carlo methods- Time difference methods (SARSA, Q-Learning)- N-step bootstrappingPart 2 (Continuous state spaces):- State aggregation- Tile CodingPart 3 (Deep Reinforcement Learning):- Deep SARSA- Deep Q-Learning- REINFORCE- Advantage Actor-Critic / A2C (Advantage Actor-Critic / A2C method)
