Explanation
This is the most comprehensive Advanced Training course on Udemy. In it, you will learn to implement some of the most powerful deep Reinforcement Learning algorithms in Python using PyTorch and PyTorch. You will implement adaptive algorithms from scratch that solve control tasks based on experience. You will learn to combine these techniques with Neural Networks and Deep Learning methods to create adaptive artificial intelligence agents capable of solving decision-making tasks.
This course will teach you state of the art reinforcement learning techniques. It will also prepare you for the next courses in this series, where we will look at other advanced methods that are better than other types of work. The course focuses on developing practical skills. Therefore, after learning the main concepts of each family of methods, we will implement one or more of their algorithms in a jupyter notebook, starting from scratch.
Level categories:
- Replication: Markkov decision process (MDP).
- Refresher: Q-learning.
- Update: A brief introduction to neural networks.
- Update: Q-deep learning.
- Reinvention: Approaches to Policy Continuity
Advanced Reinforcement Learning:
- PyTorch Lightning
- Hyperparameter Optimization with Optuna.
- Deep Q-learning in continuous activity fields (Normal Benefit Function – NAF).
- Deep Deterministic Gradient Policy (DDPG).
- DDPG delayed twinning (TD3).
- Soft Actor-Critic (SAC).
- Hindsight Experience Reweighting (HER).
What will you learn?
- Learn some of the most advanced Reinforcement Learning algorithms.
- Learn how to create AIs that can operate in complex environments to achieve their goals.
- Create from scratch high-enforcement agents using Python’s most popular
- Tools (PyTorch Lightning, OpenAI exercise, Brax, Optuna)
- Learn how to perform hyperparameter optimization (Choosing the best test conditions for AI to learn)
- Basically understand the learning process of any algorithm.
- Remove and extend the presented algorithms.
- Understand and implement new algorithms in research papers.
Who is this course for?
- Developers who want to get a job in Machine Learning.
- Data scientists/analysts and ML professionals who want to expand their knowledge base.
- Robotics students and researchers.
- Engineering students and researchers.
Specializing in high-intensity learning in Python: from DQN to SAC
- Publisher: Udemy
- Teacher: Escape Lab Speed
- Language : English
- Level: All levels
- Number of courses: 112
- Duration: 8 hours and 5 minutes
Advanced Advanced Education Content in Python: from DQN to SAC 2022-12
Requirements
- Enjoy Python programming
- Completion of our course “Intensification of Learning for beginners to learn” or qualified
- Basics of Reinforcement Learning (or watch the sim parts of this course).
- Know basic statistics (mean, variance, normal distribution)
Pictures
Sample Clip
Installation Guide
Extract files and watch your favorite player
Subtitle : English
Quality: 720p
Download Links
Password file: free download software
file size
2.37 GB