Advanced Reinforcement Learning in Python: cutting-edge DQNs

Build Artificial Intelligence (AI) agents using Deep Reinforcement Learning and PyTorch: From basic DQN to Rainbow DQN

Advanced Reinforcement Learning in Python: cutting-edge DQNs

Instructors:

Escape Velocity Labs

Description:

This is the most complete Advanced Reinforcement Learning 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 lightning. You will implement from scratch adaptive algorithms 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 introduce you to the state of the art in Reinforcement Learning techniques. It will also prepare you for the next courses in this series, where we will explore other advanced methods that excel in other types of task.

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.


Leveling modules: 


- Refresher: The Markov decision process (MDP).

- Refresher: Q-Learning.

- Refresher: Brief introduction to Neural Networks.

- Refresher: Deep Q-Learning.



Advanced Reinforcement Learning:


- PyTorch Lightning.

- Hyperparameter tuning with Optuna.

- Reinforcement Learning with image inputs

- Double Deep Q-Learning

- Dueling Deep Q-Networks

- Prioritized Experience Replay (PER)

- Distributional Deep Q-Networks

- Noisy Deep Q-Networks

- N-step Deep Q-Learning

- Rainbow Deep Q-Learning


Course content:

  • Get Bonus Downloads Here.url (0.2 KB)
    • ~Get Your Files Here !1. Introduction
    • 1. Introduction.mp4 (32.4 MB)
    • 1. Introduction.mp4.jpg (174.8 KB)
    • 1.1 Advanced Reinforcement Learning in Python from DQN to SAC.html (0.1 KB)
    • 1.2 Reinforcement Learning beginner to master.html (0.1 KB)
    • 2. Reinforcement Learning series.html (0.4 KB)
    • 3. Google Colab.mp4 (5.8 MB)
    • 3. Google Colab.srt (2.0 KB)
    • 4. Where to begin.mp4 (4.6 MB)
    • 4. Where to begin.srt (2.1 KB)
    10. Prioritized Experience Replay
    • 1. Prioritized Experience Replay.html (0.1 KB)
    • 2. Link to the code notebook.html (0.1 KB)
    • 3. DQN for visual inputs.mp4 (69.1 MB)
    • 3. DQN for visual inputs.srt (15.1 KB)
    • 4. Prioritized Experience Repay Buffer.mp4 (63.6 MB)
    • 4. Prioritized Experience Repay Buffer.srt (15.0 KB)
    • 5. Create the environment.mp4 (62.6 MB)
    • 5. Create the environment.srt (14.0 KB)
    • 6. Implement the Deep Q-Learning algorithm with Prioritized Experience Replay.mp4 (63.3 MB)
    • 6. Implement the Deep Q-Learning algorithm with Prioritized Experience Replay.srt (12.9 KB)
    • 7. Launch the training process.mp4 (42.5 MB)
    • 7. Launch the training process.srt (5.8 KB)
    • 8. Check the resulting agent.mp4 (16.8 MB)
    • 8. Check the resulting agent.srt (1.9 KB)
    11. Noisy Deep Q-Networks
    • 1. Noisy Deep Q-Networks.html (0.1 KB)
    12. N-step Deep Q-Learning
    • 1. N-step Deep Q-Learning.html (0.1 KB)
    13. Distributional Deep Q-Networks
    • 1. Distributional Deep Q-Networks.html (0.1 KB)
    2. Refresher The Markov Decision Process (MDP)
    • 1. Module overview.mp4 (2.6 MB)
    • 1. Module overview.srt (1.1 KB)
    • 10. Bellman equations.mp4 (12.4 MB)
    • 10. Bellman equations.srt (3.4 KB)
    • 11. Solving a Markov decision process.mp4 (14.2 MB)
    • 11. Solving a Markov decision process.srt (3.6 KB)
    • 2. Elements common to all control tasks.mp4 (38.7 MB)
    • 2. Elements common to all control tasks.srt (6.8 KB)
    • 3. The Markov decision process (MDP).mp4 (25.1 MB)
    • 3. The Markov decision process (MDP).srt (6.4 KB)
    • 4. Types of Markov decision process.mp4 (8.7 MB)
    • 4. Types of Markov decision process.srt (2.4 KB)
    • 5. Trajectory vs episode.mp4 (4.9 MB)
    • 5. Trajectory vs episode.srt (1.2 KB)
    • 6. Reward vs Return.mp4 (5.3 MB)
    • 6. Reward vs Return.srt (1.8 KB)
    • 7. Discount factor.mp4 (14.8 MB)
    • 7. Discount factor.srt (4.6 KB)
    • 8. Policy.mp4 (7.4 MB)
    • 8. Policy.srt (2.3 KB)
    • 9. State values v(s) and action values q(s,a).mp4 (4.3 MB)
    • 9. State values v(s) and action values q(s,a).srt (1.3 KB)
    3. Refresher Q-Learning
    • 1. Module overview.mp4 (1.5 MB)
    • 1. Module overview.srt (0.8 KB)
    • 2. Temporal difference methods.mp4 (12.6 MB)
    • 2. Temporal difference methods.srt (4.1 KB)
    • 3. Solving control tasks with temporal difference method.mp4 (14.5 MB)
    • 3. Solving control tasks with temporal difference method.srt (4.1 KB)
    • 4. Q-Learning.mp4 (11.1 MB)
    • 4. Q-Learning.srt (2.9 KB)
    • 5. Advantages of temporal difference methods.mp4 (3.7 MB)
    • 5. Advantages of temporal difference methods.srt (1.3 KB)
    4. Refresher Brief introduction to Neural Networks
    • 1. Module overview.mp4 (1.8 MB)
    • 1. Module overview.srt (0.8 KB)
    • 2. Function approximators.mp4 (36.3 MB)
    • 2. Function approximators.srt (9.8 KB)
    • 3. Artificial Neural Networks.mp4 (24.3 MB)
    • 3. Artificial Neural Networks.srt (4.4 KB)
    • 4. Artificial Neurons.mp4 (25.6 MB)
    • 4. Artificial Neurons.srt (6.6 KB)
    • 5. How to represent a Neural Network.mp4 (38.2 MB)
    • 5. How to represent a Neural Network.srt (8.2 KB)
    • 6. Stochastic Gradient Descent.mp4 (49.9 MB)
    • 6. Stochastic Gradient Descent.srt (7.2 KB)
    • 7. Neural Network optimization.mp4 (23.4 MB)
    • 7. Neural Network optimization.srt (5.0 KB)
    5. Refresher Deep Q-Learning
    • 1. Module overview.mp4 (1.3 MB)
    • 1. Module overview.srt (0.6 KB)
    • 2. Deep Q-Learning.mp4 (16.2 MB)
    • 2. Deep Q-Learning.srt (3.4 KB)
    • 3. Experience replay.mp4 (9.0 MB)
    • 3. Experience replay.srt (2.5 KB)
    • 4. Target Network.mp4 (16.6 MB)
    • 4. Target Network.srt (4.6 KB)
    6. PyTorch Lightning
    • 1. PyTorch Lightning.mp4 (32.0 MB)
    • 1. PyTorch Lightning.srt (10.5 KB)
    • 10. Prepare the data loader and the optimizer.mp4 (30.4 MB)
    • 10. Prepare the data loader and the optimizer.srt (4.9 KB)
    • 11. Define the train_step() method.mp4 (49.8 MB)
    • 11. Define the train_step() method.srt (10.9 KB)
    • 12. Define the train_epoch_end() method.mp4 (32.2 MB)
    • 12. Define the train_epoch_end() method.srt (4.7 KB)
    • 13. Train the Deep Q-Learning algorithm.mp4 (35.1 MB)
    • 13. Train the Deep Q-Learning algorithm.srt (7.5 KB)
    • 14. Explore the resulting agent.mp4 (20.3 MB)
    • 14. Explore the resulting agent.srt (3.6 KB)
    • 2. Link to the code notebook.html (0.2 KB)
    • 2.1 Google colab.html (0.2 KB)
    • 3. Introduction to PyTorch Lightning.mp4 (30.9 MB)
    • 3. Introduction to PyTorch Lightning.srt (7.0 KB)
    • 4. Create the Deep Q-Network.mp4 (22.9 MB)
    • 4. Create the Deep Q-Network.srt (5.9 KB)
    • 5. Create the policy.mp4 (18.0 MB)
    • 5. Create the policy.srt (5.7 KB)
    • 6. Create the replay buffer.mp4 (23.0 MB)
    • 6. Create the replay buffer.srt (6.6 KB)
    • 7. Create the environment.mp4 (32.2 MB)
    • <

Download this course:

file type : Torrent
Files :
  • Torrent 11.6 GB
*select one of the torrent file above to download the course
source: https://www.udemy.com/course/advanced-deep-qnetworks/

Top reviews:

JC
Jonattan Carvalho

Very good content, demonstrates a lot of methods and tools including theory and practical codes. I bought courses from different authors and this is the best series about reinforcement learning in my opinion. Part of this course is copied as a refresher from other courses of this series.

JAVH
Jose Antonio Ventajas Hernandez

Easy and simple to start with this stuff


Similar courses: