Description
Modern Reinforcement Learning: Actor-Critic Agents, the Reinforcement Learning: Actor-Critic Agents training course is published by Udemy Academy. In this advanced reinforcement learning course, you will learn how to implement policy gradient, agent-critic, DDPG, TD3 and SAC algorithms in various challenging environments from open AI gym. There will be a strong focus on working with environments with continuous action spaces, which will be of interest to those looking to conduct research in robotic control with deep reinforcement learning. Here you will learn to read deep reinforcement learning research papers yourself and implement them from scratch. You will learn a reproducible framework for rapidly implementing algorithms in advanced research papers. Mastering the content of this course will be a quantum leap in your abilities as an AI engineer and will place you among the students others rely on to break down complex ideas for them.
Don’t worry, if it’s been a while since your last refresher course, we’ll start with a quick review of the main topics. Once the basics are mastered, the pace picks up and we jump straight into an introduction to policy gradient methods. We cover the REINFORCE algorithm and use it to train an AI to land on the moon in the lunar environment from the Open AI gym. In the next step, we will go to the coding of the single-step algorithm to defeat the moon sphere again. With the basics out of the way, we move on to our more difficult projects: implementing deep reinforcement learning research papers. We begin with the Deep Destruction Policy Gradients (DDPG) algorithm, which is an algorithm for training robots to excel in a variety of continuous control tasks. DDPG combines many advances in deep learning with traditional agent-critic methods to achieve outstanding results in environments with continuous action spaces.
What you will learn
- How to code gradient policy methods in PyTorch
- How to code DDPG algorithm in PyTorch
- How to code TD3 algorithm in PyTorch
- How to code agent-critic algorithms in PyTorch
- How to implement advanced artificial intelligence research papers in Python
Who is this course suitable for?
- Advanced AI students who want to implement academic research papers
Description of Modern Reinforcement Learning: Actor-Critic Agents course
- Publisher: Udemy
- teacher : Phil Tabor
- English language
- Training level: advanced
- Number of courses: 58
- Training duration: 8 hours and 10 minutes
Head of the seasons
Course prerequisites
- Understanding of college level calculus
- Prior courses in reinforcement learning
- Able to code deep neural networks independently
Pictures
Sample video
Installation guide
After Extract, view with your favorite Player.
Subtitle: None
Quality: 720p
download link
File(s) password: www.downloadly.ir
Size
2.91 GB
Be the first to comment