[Last updated 8/2023] Modern Reinforcement Learning: Deep Q Agents (PyTorch & TF2) (Udemy – Engsub)

About Course

Views

What you’ll learn:
How to read and implement deep reinforcement learning papers
How to code Deep Q learning agents
How to Code Double Deep Q Learning Agents
How to Code Dueling Deep Q and Dueling Double Deep Q Learning Agents
How to write modular and extensible deep reinforcement learning software
How to automate hyperparameter tuning with command line arguments

Link gốc:
https://www.udemy.com/course/deep-q-learning-from-paper-to-code/

Time Course:
7 hours (50 Lectures + Documents)

Instructor
: Phil Tabor
Total Weight:
3.2 GB
** Note
:

Chú ý:

Course Content

01 – Introduction

001 What You Will Learn In This Course.mp4

04:07
002 Required Background, software, and hardware.mp4

03:46
003 How to Succeed in this Course.mp4

04:45

02 – Fundamentals of Reinforcement Learning

03 – Deep Learning Crash Course

04 – Human Level Control Through Deep Reinforcement Learning From Paper to Code

001 How to Read Deep Learning Papers.mp4

07:15
002 Analyzing the Paper.mp4

20:33
003 How to Modify the OpenAI Gym Atari Environments.mp4

14:29
004 How to Preprocess the OpenAI Gym Atari Screen Images.mp4

02:55
005 How to Stack the Preprocessed Atari Screen Images.mp4

03:26
006 How to Combine All the Changes.mp4

01:30
007 How to Add Reward Clipping, Fire First, and No Ops.mp4

04:49
008 How to Code the Agent’s Memory.mp4

10:55
009 How to Code the Deep Q Network.mp4

11:44
010 Coding the Deep Q Agent Step 1 – Coding the Constructor.mp4

07:48
011 Coding the Deep Q Agent Step 2 – Epsilon-Greedy Action Selection.mp4

02:22
012 Coding the Deep Q Agent Step 3 – Memory, Model.MP4

04:24
013 Coding the Deep Q Agent Step 4 – The Agent’s Learn Function.mp4

07:54
014 Coding the Deep Q Agent Step 5 – The Main Loop and Analyzing.mp4

14:14

05 – Deep Reinforcement Learning with Double Q Learning

06 – Dueling Network Architectures for Deep Reinforcement Learning

07 – Improving On Our Solutions

08 – Conclusion

09 – Bonus Lecture

10 – Tensorflow 2 Implementations

11 – Appendix

Student Ratings & Reviews

No Review Yet

About Course

Course Content

01 – Introduction

001 What You Will Learn In This Course.mp4

002 Required Background, software, and hardware.mp4

003 How to Succeed in this Course.mp4

02 – Fundamentals of Reinforcement Learning

001 Agents, Environments, and Actions.mp4

002 Markov Decision Processes.mp4

003 Value Functions, Action Value Functions, and the Bellman Equation.mp4

004 Model Free vs. Model Based Learning.mp4

005 The Explore-Exploit Dilemma.mp4

006 Temporal Difference Learning.mp4

03 – Deep Learning Crash Course

001 Dealing with Continuous State Spaces with Deep Neural Networks.mp4

002 Naive Deep Q Learning in Code Step 1 – Coding the Deep Q Network.mp4

003 Naive Deep Q Learning in Code Step 2 – Coding the Agent Class.mp4

004 Naive Deep Q Learning in Code Step 3 – Coding the Main Loop and Learning.mp4

005 Naive Deep Q Learning in Code Step 4 – Verifying the Functionality of Our Code.mp4

006 Naive Deep Q Learning in Code Step 5 – Analyzing Our Agent’s Performance.mp4

007 Dealing with Screen Images with Convolutional Neural Networks.mp4

04 – Human Level Control Through Deep Reinforcement Learning From Paper to Code

001 How to Read Deep Learning Papers.mp4

002 Analyzing the Paper.mp4

003 How to Modify the OpenAI Gym Atari Environments.mp4

004 How to Preprocess the OpenAI Gym Atari Screen Images.mp4

005 How to Stack the Preprocessed Atari Screen Images.mp4

006 How to Combine All the Changes.mp4

007 How to Add Reward Clipping, Fire First, and No Ops.mp4

008 How to Code the Agent’s Memory.mp4

009 How to Code the Deep Q Network.mp4

010 Coding the Deep Q Agent Step 1 – Coding the Constructor.mp4

011 Coding the Deep Q Agent Step 2 – Epsilon-Greedy Action Selection.mp4

012 Coding the Deep Q Agent Step 3 – Memory, Model.MP4

013 Coding the Deep Q Agent Step 4 – The Agent’s Learn Function.mp4

014 Coding the Deep Q Agent Step 5 – The Main Loop and Analyzing.mp4

05 – Deep Reinforcement Learning with Double Q Learning

001 Analyzing the Paper.mp4

002 Coding the Double Q Learning Agent and Analyzing Performance.mp4

06 – Dueling Network Architectures for Deep Reinforcement Learning

001 Analyzing the Paper.mp4

002 Coding the Dueling Deep Q Network.mp4

003 Coding the Dueling Deep Q Learning Agent and Analyzing Performance.mp4

004 Coding the Dueling Double Deep Q Learning Agent and Analyzing Performance.mp4

07 – Improving On Our Solutions

001 Implementing a Command Line Interface for Rapid Model Testing.mp4

002 Consolidating Our Code Base for Maximum Extensability.mp4

003 How to Test Our Agent and Watch it Play the Game in Real Time.mp4

08 – Conclusion

001 Summarizing What We’ve Learned.mp4

09 – Bonus Lecture

001 Bonus Video Where to Go From Here.mp4

10 – Tensorflow 2 Implementations

001 Differences Between Tensorflow 2 and PyTorch.mp4

002 Coding the Deep Q Network Class in Tensorflow 2.mp4

003 Coding the Deep Q Learning Agent in Tensorflow 2.mp4

004 Testing the Tensorflow 2 Deep Q Learning Agent.mp4

005 Coding the Tensorflow 2 Double Q Learning Agent.mp4

006 Coding the Dueling Network and Agent in Tensorflow 2.mp4

007 Coding the Dueling Double DQN Agent in Tensorflow 2.mp4

11 – Appendix

001 Installing the New OpenAI Gym in a Virtual Environment.mp4

002 Making the DQN Agent Compliant with the New Gym Interface.mp4

Student Ratings & Reviews