- Hands-On Reinforcement Learning with Python
- Sudharsan Ravichandiran
- 150字
- 2021-06-18 19:12:05
Getting Started with OpenAI and TensorFlow
OpenAI is a non-profit, open source artificial intelligence (AI) research company founded by Elon Musk and Sam Altman that aims to build a general AI. They are sponsored by top industry leaders and top-notch companies. OpenAI comes in two flavors, Gym and Universe, using which we can simulate realistic environments, build reinforcement learning (RL) algorithms, and test our agents in those environments. TensorFlow is an open source machine learning library by Google that is extensively used for numerical computation. We will use OpenAI and TensorFlow for building and evaluating powerful RL algorithms in the upcoming chapters.
In this chapter, you will learn about the following:
- Setting up your machine by installing Anaconda, Docker, OpenAI Gym, and Universe and TensorFlow
- Simulating an environment using OpenAI Gym and Universe
- Training a robot to walk
- Building a video game bot
- Fundamentals of TensorFlow
- Using TensorBoard
推薦閱讀
- 從零開始:數字圖像處理的編程基礎與應用
- UML和模式應用(原書第3版)
- JIRA 7 Administration Cookbook(Second Edition)
- Python計算機視覺編程
- Mastering LibGDX Game Development
- Learning AndEngine
- Learning Hunk
- Visual C#通用范例開發金典
- SQL Server數據庫管理與開發兵書
- Python Automation Cookbook
- Swift High Performance
- Unity虛擬現實開發圣典
- Practical Time Series Analysis
- 秒懂算法:用常識解讀數據結構與算法
- Isomorphic JavaScript Web Development