Главная
Study mode:
on
1
- Start
2
- Introduction
3
- Gameplan
4
- RL in a Nutshell
5
- 1. Setup Stable Baselines
6
- 2. Environments
7
- Loading OpenAI Gym Environments
8
- Understanding OpenAI Gym Environments
9
- 3. Training
10
- Train a Reinforcement Learning Model
11
- Saving and Reloading Environments
12
- 4. Testing and Evaluation
13
- Evaluating RL Models
14
- Testing the Agent
15
- Viewing Logs in Tensorboard
16
- Performance Tuning
17
- 5. Callbacks, Alternate Algorithms, Neural Networks
18
- Adding Training Callbacks
19
- Changing Policies
20
- Changing Algorithms
21
- 6. Projects
22
- Project 1 Atari
23
- Importing Dependencies
24
- Applying GPU Acceleration with PyTorch
25
- Testing Atari Environments
26
- Vectorizing Environments
27
- Save and Reload Atari Model
28
- Evaluate and Test Atari RL Model
29
- Updated Performance
30
- Project 2 Autonomous Driving
31
- Installing Dependencies
32
- Test CarRacing-v0 Environment
33
- Train Autonomous Driving Agent
34
- Save and Reload Self Driving model
35
- Updated Self Driving Performance
36
- Project 3 Custom Open AI Gym Environments
37
- Import Dependencies for Custom Environment
38
- Types of OpenAI Gym Spaces
39
- Building a Custom Open AI Environment
40
- Testing a Custom Environment
41
- Train a RL Model for a Custom Environment
42
- Save a Custom Environment Model
43
- 7. Wrap Up
Description:
Dive into a comprehensive 3-hour video course on Reinforcement Learning using Python, OpenAI Gym, and Stable Baselines. Master the fundamentals of RL, from basic concepts to building custom environments. Learn to develop deep learning-powered agents capable of solving various RL problems, including CartPole, Breakout, and CarRacing. Explore topics such as environment setup, model training, evaluation, and performance tuning. Engage in hands-on projects, including Atari game playing, autonomous driving, and creating custom OpenAI Gym environments. Gain practical skills in applying GPU acceleration, vectorizing environments, and working with different algorithms and neural network policies. By the end of this course, acquire the knowledge and tools necessary to tackle a wide range of reinforcement learning challenges and create your own RL projects.

Reinforcement Learning - Full Course Using Python

Nicholas Renotte
Add to list
#Computer Science #Machine Learning #Reinforcement Learning #Programming #Programming Languages #Python #Artificial Intelligence #Neural Networks #Deep Learning #PyTorch #Autonomous Vehicles #Autonomous Driving #OpenAI Gym
1 of 43

- Start