Reinforcement Learning for Beginner to Pro

Buy $199.99

Course curriculum

1. Introduction to Instructor
2. Introduction to Course
1. What Is Reinforcement Learning
2. WhatIs Reinforcement Learning hiders and seekers by OpenAI
3. RL vs Other ML Frameworks
4. Why RL
5. Examples Of RL
6. Limitations Of RL
7. Exercises
1. Introduction
2. Envionment
3. Agent
4. Action
5. State
6. Goal and Done State
7. Reward
8. Fun Activity
9. Policy and Plan
10. Episode
1. Introduction to Module
2. Introduction to Game
3. Rules of Game
4. Setting up game Python pt 1
5. Setting up game Python pt 2
6. Setting up game Python pt 3
7. Playing the game manually
8. Implementing Random solution
9. Q Learning and Q Table Theory
10. Implemeting Q Learning pt 1
11. Dry Run of get state
12. Answer to Question
13. Implemeting Q Learning pt 2
14. Implemeting Q Learning pt 3
15. Conclusion
1. Introduction to Gym
2. Frozen Lake Rules
3. Implementing Frozen Lake pt 1
4. Implementing Frozen Lake pt 2
5. Implementing Frozen Lake pt 3
6. Implementing Frozen Lake pt 4
7. Agent plays the game
8. Conclusion
1. Introduction to Module
2. Epsilon
3. Updating Epsilon Value
4. Gamma, Discount Factor
5. Alpha Learning Rate
6. Q Learning Equation
7. Quiz (Number of Episodes)
8. Solution (Number of Episodes)
9. Quiz (Alpha)
10. Solution (Alpha)
1. Introduction to SARSA
2. Off policy VS On policy
3. SARSA Implementation
4. SARSA Implementation update
5. Pros & Cons
1. Why Deep Learning
2. Why PyTorch
3. PyTorch installation and Tensors intro
4. Automatic Diffrenciation Pytorch New
5. Why DNNs in Machine Learning
6. Representational Power and Data Utilization Capacity of DNN
7. Perceptron
8. Perceptron Exercise
9. Perceptron Exercise Solution
10. Perceptron Implementation
11. DNN Architecture
12. DNN Architecture Exercise
13. DNN Architecture Exercise Solution
14. DNN ForwardStep Implementation
15. DNN Why Activation Function is Required
16. DNN Why Activation Function is Required Exercise
17. DNN Why Activation Function is Required Exercise Solution
18. MDP
19. DNN Properties of Activation Function
20. DNN Activation Functions in Pytorch
21. DNN What is Loss Function
22. DNN What is Loss Function Exercise
23. DNN What is Loss Function Exercise Solution
24. DNN What is Loss Function Exercise 2
25. DNN What is Loss Function Exercise 2 Solution
26. DNN Loss Function in Pytorch
27. DNN Gradient Descent
28. DNN Gradient Descent Exercise
29. DNN Gradient Descent Exercise Solution
30. DNN Gradient Descent Implementation
31. DNN Gradient Descent Stochastic Batch Minibatch
32. DNN Gradient Descent Summary
33. DNN Implemenation Gradient Step
34. DNN Implemenation Stochastic Gradient Descent
35. DNN Implemenation Batch Gradient Descent
36. DNN Implemenation Minibatch Gradient Descent
37. DNN Implemenation in PyTorch
38. DNN Weights Initializations
39. DNN Learning Rate
40. DNN Batch Normalization
41. DNN Batch Normalization Implementation
42. DNN Optimizations
43. DNN Dropout
44. DNN Dropout in PyTorch
45. DNN Early Stopping
46. DNN Hyperparameters
47. DNN Pytorch CIFAR10 Example
1. Introduction & Recap
2. DQN Algorithm Steps
3. Introduction to Project (Cart pole)
4. Policy Network Explained
5. Neural Network Class Implementation
6. Replay Memory & Experience
7. Experience Implementation
8. Replay Memory Implementatiton
9. Target Network & Recap
10. Epsilon Greeady Strategy Implemented
11. Agent Class Implemented
12. Environment Manager Implementation
13. How to Get State
14. Screen Preprocessing
15. Screen Croping
16. Screen Transformation
17. Processed VS NonProcessed Screen
18. Moving Avg Implemented
19. Ploting the Moving Avg
20. Hyperparameter Initialization
21. Initializing the Classes
22. Final Structure Implementation part 1
23. Extracting Tensors
24. Final Structure Implementation part 2
25. Qvalues Calculator Implemented
26. Removing Errors Final Structure Implementation part 3
27. Visualizing the Training
1. Introduction to Stable Baseline
2. Loading & Understanding the Envireonment
3. Train RL Model
4. Evaluation and Testing
5. Callbacks & Early Stopping
6. Changing Policy Architecture
7. Changing the Algorithm
8. Tips for Accuracy Improvement
1. Introduction to Libraries and Project
2. Loading the Data
3. Setting up Environment
4. Random Actions
5. Training and Evaluating Model
1. Introduction to Game
2. Importing the Dependencies
3. Exploring the Environment
4. Training and Testing the Model
1. Prep 1
2. Prep 2

About this course

$199.99
150 lessons
14 hours of video content

Reinforcement Learning for Beginner to Pro

Course curriculum

Introduction

Motivation & Applications

Terminologies of RL

Naïve Random Solution

RL based Q Learning Solution

Hyper Parameters & Concepts

SARSA

DNN Foundation for Deep RL

Deep RL DQN

StableBaseLines Cartpole Solution

Trading Bot RL

Car Racing Game

Interview Prep

About this course