Machine Learning Tutorial Python : 7. Reinforcement Learning

#vision2020 #aiforeveryone #machinelearning

"My Vision is to provide "AIFOREVERYONE", by creating free video courses for Artificial Intelligence ,
Machine Learning, Deep Learning and Data Science Aspirants!"

If you wish to support my #vision2020, kindly Like, Subscribe & Share this knowledge to your friends and colleagues.

Follow Me :

Materials: https://aiforevery1.com/

LinkedIn : https://www.linkedin.com/in/vinothrathinamautomation/

Github : https://github.com/vinothrwins

Udemy : https://www.udemy.com/user/vinoth-rathinam/

Facebook : https://www.facebook.com/aiforevery1

************************************************************
Playlist:

* Artificial Intelligence for everyone(Entire Playlist) : https://www.youtube.com/playlist?list=PLNUKIBJDwfVvpQosXAW_a2w4WK4pdffun

* Python for Artificial Intelligence : https://www.youtube.com/playlist?list=PLNUKIBJDwfVuxdOhQQUpviYR0wBbg-OBp

* Mathematics for Artificial Intelligence : https://www.youtube.com/playlist?list=PLNUKIBJDwfVtoIWQmMonKOhDdMlo8rGQN

* Python NumPy for Artificial Intelligence : https://www.youtube.com/playlist?list=PLNUKIBJDwfVu2atCreVKFOFfDR9y8HKmt

* Python Pandas for Artificial Intelligence : https://www.youtube.com/playlist?list=PLNUKIBJDwfVt85Lo8wx6gY6dBVasATd2p

* Data Science Process : https://www.youtube.com/playlist?list=PLNUKIBJDwfVt_MiuPYO_CIMFwCk95vR6a

* Artificial Intelligence for Beginners : https://www.youtube.com/playlist?list=PLNUKIBJDwfVt2Ggb00igRSmcan11r0Fuc

***********************************************************

*************************
Easy Definition
*************************
Machine learning is a subset of Artificial Intelligence. Which works based on self learning algorithm using past experience or dataset without being explicitly programmed.

Self Learning Algorithm : The algorithm which will learn by itself and takes own decision/predictions
****************************
Types of Machine Learning
1. Supervised Learning
2. Unsupervised Learning
3. Reinforcement Learning
****************************
Definition of Supervised Learning

Reinforcement Learning(RL) is a type of machine learning technique that enables an agent to learn in an interactive environment by trial and error using feedback from its own actions and experiences.


Supervised learning algorithms infer a function from labeled data and use this function on new examples/never seen data/test data.

********************************************************************
Definition of Supervised Learning
Unsupervised learning is the training of an artificial intelligence  Algorithm using information that is neither classified nor labeled and allowing the algorithm to act on that information without guidance.

Mathematically - Only Input Data x and No corresponding output variable
********************************************************************
Definition of Reinforcement Learning
Reinforcement Learning(RL) is a type of machine learning technique that enables an agent to learn in an interactive environment by trial and error using feedback from its own actions and experiences.

Eg : Baby playing - No teacher , based on environment it will learn and play
********************************************************************
Types of Tasks

1. Episodic Task

It is having starting point and an ending point (a terminal state)
This creates an episode - a list of States, Actions, Rewards, and New States.
Example:
Super Mario
Begin : Episode begin at the launch
Ending : when you’re killed or you’re reach the end of the level

2. Continuous Task

This Task will continue forever(No terminal state)
The agent has to learn how to choose the best actions and simultaneously interacts with the environment.
Example:
Automated stock trading

**********************************************************************
Types of Learning

1. Monte Carlo Approach

Collecting the rewards at the end of the episode and then calculating the maximum expected future reward
We start a new game with the added knowledge. The agent makes better decisions with each iteration

2. Temporal Difference Learning

It will update its value estimation for the non-terminal states occurring at that experience.
It is also called TD(0) or one step TD

**********************************************************************
Exploration/Exploitation trade off

Exploration is finding more information about the environment.
Exploitation is exploiting known information to maximize the reward.
**********************************************************************
List of Reinforcement Learning Algorithms

Monte Carlo
Q-Learning
Q-Learning with Normalized Advantage Functions NAF
State-Action-Reward-State-Action (SARSA)
Deep Q Network (DQN)
Deep Deterministic Policy Gradient (DDPG)


************************************************************
Kindly let me know your feedback for improvement purpose. Feel free to correct any mistakes in case !!

Happy Learning,
Vinoth Rathinam