[Last updated 8/2023] Modern Reinforcement Learning: Actor-Critic Agents (Udemy – Engsub)

About Course

Views

What you’ll learn:
How to code policy gradient methods in PyTorch
How to code Deep Deterministic Policy Gradients (DDPG) in PyTorch
How to code Twin Delayed Deep Deterministic Policy Gradients (TD3) in PyTorch
How to code actor critic algorithms in PyTorch
How to implement cutting edge artificial intelligence research papers in Python

Link gốc:
https://www.udemy.com/course/actor-critic-methods-from-paper-to-code-with-pytorch/

Time Course:
10.5 hours (74 Lectures + Documents)

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

Chú ý:

Course Content

01 – Introduction

001 What You Will Learn in this Course.mp4

03:41
002 Required Background, Software, and Hardware.mp4

03:17
003 How to Succeed in this Course.mp4

03:51

02 – Fundamentals of Reinforcement Learning

03 – Landing on the Moon with Policy Gradients & Actor Critic Methods

001 What’s so Great About Policy Gradient Methods.mp4

07:38
002 Combining Neural Networks with Monte Carlo REINFORCE Policy Gradient Algorithm.mp4

05:02
003 Introducing the Lunar Lander Environment.mp4

03:54
004 Coding the Agent’s Brain The Policy Gradient Network.mp4

05:29
005 Coding the Policy Gradient Agent’s Basic Functionality.mp4

05:50
006 Coding the Agent’s Learn Function.mp4

06:04
007 Coding the Policy Gradient Main Loop and Watching our Agent Land on the Moon.mp4

09:27
008 Actor Critic Learning Combining Policy Gradients & Temporal Difference Learning.mp4

04:12
009 Coding the Actor Critic Networks.mp4

03:23
010 Coding the Actor Critic Agent.mp4

08:20
011 Coding the Actor Critic Main Loop and Watching Our Agent Land on the Moon.mp4

09:22

04 – Deep Deterministic Policy Gradients (DDPG) Actor Critic with Continuous Actions

001 Getting up to Speed With Deep Q Learning.mp4

04:44
002 How to Read and Understand Cutting Edge Research Papers.mp4

06:11
003 Analyzing the DDPG Paper Abstract and Introduction.mp4

07:00
004 Analyzing the Background Material.mp4

05:55
005 What Algorithm Are We Going to Implement.mp4

08:03
006 What Results Should We Expect.mp4

09:36
007 What Other Solutions are Out There.mp4

04:31
008 What Model Architecture and Hyperparameters Do We Need.mp4

03:12
009 Handling the Explore-Exploit Dilemma Coding the OU Action Noise Class.mp4

03:37
010 Giving our Agent a Memory Coding the Replay Memory Buffer Class.mp4

07:04
011 Deep Q Learning for Actor Critic Methods Coding the Critic Network.mp4

15:49
012 Coding the Actor Network Class.mp4

10:10
013 Giving our DDPG Agent Simple Autonomy Coding the Basic Functions.mp4

12:11
014 Giving our DDPG Agent a Brain Coding the Agent’s Learn Function.mp4

09:43
015 Coding the Network Parameter Update Functionality.mp4

08:16
016 Coding the Main Loop and Watching Our DDPG Agent Land on the Moon.mp4

13:11

05 – Twin Delayed Deep Deterministic Policy Gradients (TD3)

001 Some Tips on Reading this Paper.mp4

01:39
002 Analyzing the TD3 Paper Abstract and Introduction.mp4

09:32
003 What Other Solutions Have People Tried.mp4

03:36
004 Reviewing the Fundamental Concepts.mp4

02:53
005 Is Overestimation Bias Even a Problem in Actor-Critic Methods.mp4

13:16
006 Why is Variance a Problem for Actor-Critic Methods.mp4

06:56
007 What Results Can We Expect.mp4

06:06
008 Coding the Brains of the TD3 Agent – The Actor and Critic Network Classes.mp4

13:34
009 Giving our TD3 Agent Simple Autonomy – Coding the Basic Agent Functionality.mp4

10:57
010 Giving our TD3 Agent a Brain – Coding the Learn Function.mp4

10:31
011 Coding the Network Parameter Update Functionality.mp4

11:32
012 Coding the Main Loop And Watching our Agent Learn to Walk.mp4

09:44

06 – Soft Actor Critic

001 A Quick Word on the Paper.mp4

00:59
002 Getting Acquainted With a New Framework.mp4

05:45
003 Checking Out What Has Been Done Before.mp4

04:44
004 Inspecting the Foundation of this New Framework.mp4

03:37
005 Digging Into the Mathematics of Soft Actor Critic.mp4

11:00
006 Seeing How the New Algorithm Measures Up.mp4

07:50
007 Coding the Neural Networks.mp4

23:25
008 Coding the Soft Actor Critic Basic Functionality.mp4

10:59
009 Coding the Soft Actor Critic Algorithm.mp4

12:34
010 Coding the Main Loop and Evaluating Our Agent.mp4

12:33

07 – Tensorflow 2 Implementation

001 Coding the Policy Gradient Network in Tensorflow 2.mp4

03:54
002 Coding the REINFORCE Agent in Tensorflow 2.mp4

10:46
003 Coding the REINFORCE Main Loop and Evaluating our Agent.mp4

08:34
004 Coding the Actor Critic Network in Tensorflow 2.mp4

01:45
005 Coding the Actor Critic Agent in Tensorflow 2.mp4

05:50
006 Coding the Actor Critic Main Program and Evaluating our Agent.mp4

03:39
007 Coding the DDPG Networks in Tensorflow 2.mp4

03:55
008 Coding the DDPG Agent in Tensorflow 2.mp4

15:47
009 Coding the DDPG Main Program and Evaluating our Agent.mp4

04:17
010 Coding the TD3 Agent in Tensorflow 2.mp4

15:58
011 Coding the TD3 Main Program and Evaluating our Agent.mp4

01:53
012 Coding the SAC Networks in Tensorflow 2.mp4

04:32
013 Coding the SAC Agent in Tensorflow 2.mp4

19:15
014 Coding the SAC Main Function and Evaluating our Agent.mp4

02:44

08 – 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 Review of Fundamental Concepts.mp4

003 Teaching an AI about Black Jack with Monte Carlo Prediction.mp4

004 Teaching an AI How to Play Black Jack with Monte Carlo Control.mp4

005 Review of Temporal Difference Learning Methods.mp4

006 Teaching an AI about Balance with TD(0) Prediction.mp4

007 Teaching an AI to Balance the Cart Pole with Q Learning.mp4

03 – Landing on the Moon with Policy Gradients & Actor Critic Methods

001 What’s so Great About Policy Gradient Methods.mp4

002 Combining Neural Networks with Monte Carlo REINFORCE Policy Gradient Algorithm.mp4

003 Introducing the Lunar Lander Environment.mp4

004 Coding the Agent’s Brain The Policy Gradient Network.mp4

005 Coding the Policy Gradient Agent’s Basic Functionality.mp4

006 Coding the Agent’s Learn Function.mp4

007 Coding the Policy Gradient Main Loop and Watching our Agent Land on the Moon.mp4

008 Actor Critic Learning Combining Policy Gradients & Temporal Difference Learning.mp4

009 Coding the Actor Critic Networks.mp4

010 Coding the Actor Critic Agent.mp4

011 Coding the Actor Critic Main Loop and Watching Our Agent Land on the Moon.mp4

04 – Deep Deterministic Policy Gradients (DDPG) Actor Critic with Continuous Actions

001 Getting up to Speed With Deep Q Learning.mp4

002 How to Read and Understand Cutting Edge Research Papers.mp4

003 Analyzing the DDPG Paper Abstract and Introduction.mp4

004 Analyzing the Background Material.mp4

005 What Algorithm Are We Going to Implement.mp4

006 What Results Should We Expect.mp4

007 What Other Solutions are Out There.mp4

008 What Model Architecture and Hyperparameters Do We Need.mp4

009 Handling the Explore-Exploit Dilemma Coding the OU Action Noise Class.mp4

010 Giving our Agent a Memory Coding the Replay Memory Buffer Class.mp4

011 Deep Q Learning for Actor Critic Methods Coding the Critic Network.mp4

012 Coding the Actor Network Class.mp4

013 Giving our DDPG Agent Simple Autonomy Coding the Basic Functions.mp4

014 Giving our DDPG Agent a Brain Coding the Agent’s Learn Function.mp4

015 Coding the Network Parameter Update Functionality.mp4

016 Coding the Main Loop and Watching Our DDPG Agent Land on the Moon.mp4

05 – Twin Delayed Deep Deterministic Policy Gradients (TD3)

001 Some Tips on Reading this Paper.mp4

002 Analyzing the TD3 Paper Abstract and Introduction.mp4

003 What Other Solutions Have People Tried.mp4

004 Reviewing the Fundamental Concepts.mp4

005 Is Overestimation Bias Even a Problem in Actor-Critic Methods.mp4

006 Why is Variance a Problem for Actor-Critic Methods.mp4

007 What Results Can We Expect.mp4

008 Coding the Brains of the TD3 Agent – The Actor and Critic Network Classes.mp4

009 Giving our TD3 Agent Simple Autonomy – Coding the Basic Agent Functionality.mp4

010 Giving our TD3 Agent a Brain – Coding the Learn Function.mp4

011 Coding the Network Parameter Update Functionality.mp4

012 Coding the Main Loop And Watching our Agent Learn to Walk.mp4

06 – Soft Actor Critic

001 A Quick Word on the Paper.mp4

002 Getting Acquainted With a New Framework.mp4

003 Checking Out What Has Been Done Before.mp4

004 Inspecting the Foundation of this New Framework.mp4

005 Digging Into the Mathematics of Soft Actor Critic.mp4

006 Seeing How the New Algorithm Measures Up.mp4

007 Coding the Neural Networks.mp4

008 Coding the Soft Actor Critic Basic Functionality.mp4

009 Coding the Soft Actor Critic Algorithm.mp4

010 Coding the Main Loop and Evaluating Our Agent.mp4

07 – Tensorflow 2 Implementation

001 Coding the Policy Gradient Network in Tensorflow 2.mp4

002 Coding the REINFORCE Agent in Tensorflow 2.mp4

003 Coding the REINFORCE Main Loop and Evaluating our Agent.mp4

004 Coding the Actor Critic Network in Tensorflow 2.mp4

005 Coding the Actor Critic Agent in Tensorflow 2.mp4

006 Coding the Actor Critic Main Program and Evaluating our Agent.mp4

007 Coding the DDPG Networks in Tensorflow 2.mp4

008 Coding the DDPG Agent in Tensorflow 2.mp4

009 Coding the DDPG Main Program and Evaluating our Agent.mp4

010 Coding the TD3 Agent in Tensorflow 2.mp4

011 Coding the TD3 Main Program and Evaluating our Agent.mp4

012 Coding the SAC Networks in Tensorflow 2.mp4

013 Coding the SAC Agent in Tensorflow 2.mp4