Deep Reinforcement Learning made-easy

سرفصل های دوره

Reinforcement Learning for beginners to advanced learners

1 - Introduction

1 -Introduction to Deep Reinforcement Learning

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

3 -Comparison with supervised and unsupervised learning

4 -Overview of the RL history

5 -Recent advances in Deep Reinforcement Learning

6 -Learning objectives for the course and Introduction to Python

2 - Artificial Neural Network (ANN)

1 -ANN algorithm Nontechnical explanation

2 -ANN algorithm Mathematical Formulae

3 -ANN algorithm A Worked-Out Example

3 - ANN to Deep Neural Network (DNN)

1 -Deep Neural Network

2 -Deep learning frameworks

3 -Introduction to TensorFlow and Keras

4 -Key terms in TensorFlow

5 -KERAS

6 -The concept of gradient descent

7 -Learning rate

4 - Deep Learning Hyperparameters Regularization

1 -Hyper parameters in Machine Learning

2 -L1 and L2 Regularization in Regression

3 -Regularization in Neural networks

4 -Regularization in Regression

5 -Data standardization in L1 and L2 regularization

6 -Dropout Regularization

7 -Early stopping method for neural networks

8 -Saving the Model

5 - Deep Learning Hyper parameters, Activation Functions and Optimizations

1 -Loss Functions

2 -Activation Functions

3 -Activation Function Sigmoid

4 -Activation Function Tanh

5 -Activation Function ReLU

6 -Activation Function SoftMax

7 -Optimizers SGD, Mini-batch descent

6 - Convolutional Neural Network (CNN)

1 -Introduction to CNN

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

3 -Filters or kernels

7 - Recurrent Neural Network (RNN)

1 -Cross-sectional data vs sequential data

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

3 -Case study of word prediction

4 -Introduction to RNN

5 -Python Code Model Training of CNN and RNN

8 - Reinforcement Learning Overview of Markov Decision Processes

1 -Review of Reinforcement Learning

2 -Introduction to Value Function Approximation

3 -Python Code Value Function Approximation using CartPole

4 -Linear function approximation

5 -Python Code Linear Function Approximation using CartPole

6 -Non-linear function approximation with deep neural networks

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

8 -Applications and limitations of Value Function Approximation

9 -Definition of Markov Decision Processes (MDPs)

10 -Python Code MDPs and Bellman Equations and Value Functions

11 -Key components of an MDP

12 -Bellman Equations and Value Functions

13 -Policy iteration and value iteration algorithms

14 -Python Code Policy iteration and value iteration algorithms

9 - Bellman Equations and Value Functions

1 -Python Code Introduction to Python Gym Library Documentation

2 -Review of Bellman Equations

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

4 -Calculation of value functions using Bellman Equations

5 -Intuitive interpretation of value functions

6 -Markov Processes

7 -Markov Reward Processes

8 -Markov Decision Processes

9 -Extensions to MDPs

10 - Deep Reinforcement Learning with Q-Learning

1 -Definition of Q-Learning

2 -Calculation of Q-Values using Q-Learning

3 -Python Code Q-Learning and Python Gym library

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

5 -Advantages and disadvantages of Q-Learning

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

7 -Architecture of a DQN model

8 -Implementation of DQN in TensorFlow

9 -Python Code Implementation of DQN

10 -Applications and limitations of DQN

11 - Model-Free Prediction

1 -Definition of Model-Free Prediction

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

3 -Monte Carlo

4 -Python Code Monte Carlo Algorithm

5 -TD Learning

6 -Python Code Temporal Difference (TD) Learning Algorithm

7 -Python Code SARSA Algorithm

8 -Discussion of the limitations of Model-Free Prediction

9 -Python Code Expected SARSA Algorithm

10 -Python Code n-Steps SARSA Algorithm

139,000 تومان

افزودن به سبد خرید

خرید دانلودی فوری

در این روش نیاز به افزودن محصول به سبد خرید و تکمیل اطلاعات نیست و شما پس از وارد کردن ایمیل خود و طی کردن مراحل پرداخت لینک های دریافت محصولات را در ایمیل خود دریافت خواهید کرد.

تولید کننده: Udemy