Deep Reinforcement Learning made-easy

Focused View

11:20:40

0 View

1 - Introduction

1 -Introduction to Deep Reinforcement Learning.mp4

08:28

2 -Reinforcement Learning and its main components (agent, environment, rewards).mp4

20:25

3 -Comparison with supervised and unsupervised learning.mp4

18:21

4 -Overview of the RL history.mp4

04:06

5 -Recent advances in Deep Reinforcement Learning.mp4

05:07

6 -Learning objectives for the course and Introduction to Python.mp4

11:06

2 - Artificial Neural Network (ANN)

1 -ANN algorithm Nontechnical explanation.mp4

08:45

2 -ANN algorithm Mathematical Formulae.mp4

04:20

3 -ANN algorithm A Worked-Out Example.mp4

20:50

3 - ANN to Deep Neural Network (DNN)

1 -Deep Neural Network.mp4

22:52

2 -Deep learning frameworks.mp4

02:47

3 -Introduction to TensorFlow and Keras.mp4

13:27

4 -Key terms in TensorFlow.mp4

22:23

5 -KERAS.mp4

06:47

6 -The concept of gradient descent.mp4

15:45

7 -Learning rate.mp4

20:44

4 - Deep Learning Hyperparameters Regularization

1 -Hyper parameters in Machine Learning.mp4

19:51

2 -L1 and L2 Regularization in Regression.mp4

02:54

3 -Regularization in Neural networks.mp4

02:10

4 -Regularization in Regression.mp4

02:10

5 -Data standardization in L1 and L2 regularization.mp4

02:29

6 -Dropout Regularization.mp4

06:12

7 -Early stopping method for neural networks.mp4

03:10

8 -Saving the Model.mp4

03:40

5 - Deep Learning Hyper parameters, Activation Functions and Optimizations

1 -Loss Functions.mp4

33:11

2 -Activation Functions.mp4

00:32

3 -Activation Function Sigmoid.mp4

03:19

4 -Activation Function Tanh.mp4

03:41

5 -Activation Function ReLU.mp4

04:06

6 -Activation Function SoftMax.mp4

04:08

7 -Optimizers SGD, Mini-batch descent.mp4

04:59

6 - Convolutional Neural Network (CNN)

1 -Introduction to CNN.mp4

07:59

2 -Artificial Neural network vs Convolutional Neural Network (ANN vs CNN).mp4

04:25

3 -Filters or kernels.mp4

11:53

7 - Recurrent Neural Network (RNN)

1 -Cross-sectional data vs sequential data.mp4

04:41

2 -Models for sequential data ANN, CNN and Sequential ANN.mp4

18:44

3 -Case study of word prediction.mp4

01:37

4 -Introduction to RNN.mp4

16:15

5 -Python Code Model Training of CNN and RNN.mp4

33:49

8 - Reinforcement Learning Overview of Markov Decision Processes

1 -Review of Reinforcement Learning.mp4

22:49

2 -Introduction to Value Function Approximation.mp4

01:26

3 -Python Code Value Function Approximation using CartPole.mp4

12:37

4 -Linear function approximation.mp4

00:51

5 -Python Code Linear Function Approximation using CartPole.mp4

01:44

6 -Non-linear function approximation with deep neural networks.mp4

00:37

7 -Python Code Non-Linear Function Approximation with Neural Networks.mp4

03:28

8 -Applications and limitations of Value Function Approximation.mp4

00:50

9 -Definition of Markov Decision Processes (MDPs).mp4

00:59

10 -Python Code MDPs and Bellman Equations and Value Functions.mp4

09:15

11 -Key components of an MDP.mp4

03:45

12 -Bellman Equations and Value Functions.mp4

00:45

13 -Policy iteration and value iteration algorithms.mp4

18:34

14 -Python Code Policy iteration and value iteration algorithms.mp4

10:41

9 - Bellman Equations and Value Functions

1 -Python Code Introduction to Python Gym Library Documentation.mp4

08:01

2 -Review of Bellman Equations.mp4

04:14

3 -Definition of value functions (state value, action value).mp4

02:20

4 -Calculation of value functions using Bellman Equations.mp4

01:58

5 -Intuitive interpretation of value functions.mp4

03:00

6 -Markov Processes.mp4

12:01

7 -Markov Reward Processes.mp4

14:11

8 -Markov Decision Processes.mp4

17:39

9 -Extensions to MDPs.mp4

06:56

10 - Deep Reinforcement Learning with Q-Learning

1 -Definition of Q-Learning.mp4

01:11

2 -Calculation of Q-Values using Q-Learning.mp4

03:43

3 -Python Code Q-Learning and Python Gym library.mp4

07:06

4 -Comparison of Q-Learning with policy iteration and value iteration algorithms.mp4

00:49

5 -Advantages and disadvantages of Q-Learning.mp4

02:13

6 -Overview of Deep Q-Network (DQN) algorithm.mp4

05:01

7 -Architecture of a DQN model.mp4

01:29

8 -Implementation of DQN in TensorFlow.mp4

03:24

9 -Python Code Implementation of DQN.mp4

20:36

10 -Applications and limitations of DQN.mp4

03:22

11 - Model-Free Prediction

1 -Definition of Model-Free Prediction.mp4

04:35

2 -Calculation of state values using Model-Free Prediction methods.mp4

01:02

3 -Monte Carlo.mp4

01:59

4 -Python Code Monte Carlo Algorithm.mp4

05:25

5 -TD Learning.mp4

26:08

6 -Python Code Temporal Difference (TD) Learning Algorithm.mp4

03:40

7 -Python Code SARSA Algorithm.mp4

08:27

8 -Discussion of the limitations of Model-Free Prediction.mp4

02:14

9 -Python Code Expected SARSA Algorithm.mp4

13:54

10 -Python Code n-Steps SARSA Algorithm.mp4

03:33

Description

Reinforcement Learning for beginners to advanced learners

What You'll Learn?

To understand deep learning and reinforcement learning paradigms
To understand Architectures and optimization methods for deep neural network training
To implement deep learning methods within Tensor Flow and apply them to data
To understand the theoretical foundations and algorithms of reinforcement learning
To apply reinforcement learning algorithms to environments with complex dynamics

Who is this for?

Data Scientists

Machine Learning Engineers

Robotics Programmer

What You Need to Know?

Basic python programming but not necessary

More details

Description
This course is the integration of deep learning and reinforcement learning. The course will introduce student with deep neural networks (DNN) starting from simple neural networks (NN) to recurrent neural network and long-term short-term memory networks. NN and DNN are the part of reinforcement learning (RL) agent so the students will be explained how to design custom RL environments and use them with RL agents. After the completion of the course the students will be able:
To understand deep learning and reinforcement learning paradigms
To understand Architectures and optimization methods for deep neural network training
To implement deep learning methods within Tensor Flow and apply them to data.
To understand the theoretical foundations and algorithms of reinforcement learning.
To apply reinforcement learning algorithms to environments with complex dynamics.

Course Contents:
Introduction to Deep Reinforcement Learning
Artificial Neural Network (ANN)
ANN to Deep Neural Network (DNN)
Deep Learning Hyperparameters: Regularization
Deep Learning Hyperparameters: Activation Functions and Optimizations
Convolutional Neural Network (CNN)
CNN Architecture
Recurrent Neural Network (RNN)
RNN for Long Sequences
LSTM Network
Overview of Markov Decision Processes
Bellman Equations and Value Functions
Deep Reinforcement Learning with Q-Learning
Model-Free Prediction
Deep Reinforcement Learning with Policy Gradients
Exploration and Exploitation in Reinforcement Learning
Who this course is for:
Data Scientists
Machine Learning Engineers
Robotics Programmer

User Reviews

Rating

average 0

Total votes0

Focused display

Deep Learning

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.