๐—ง๐˜†๐—ฝ๐—ฒ๐˜€ ๐—ผ๐—ณ ๐— ๐—ฎ๐—ฐ๐—ต๐—ถ๐—ป๐—ฒ ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป๐—ถ๐—ป๐—ด: ๐—ฅ๐—ฒ๐—ถ๐—ป๐—ณ๐—ผ๐—ฟ๐—ฐ๐—ฒ๐—บ๐—ฒ๐—ป๐˜ ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป๐—ถ๐—ป๐—ด

In the reinforcement learning paradigm, the learning process is a loop in which the agent reads the state of the environment and then executes an action.
Then the environment returns its new state and a reward signal, indicating if the action was correct or not. The process continues until the environment reaches a terminal state or if a maximum number of iterations is executed.
These are some of the main concepts in Reinforcement Learning:
๐—ง๐—ต๐—ฒ ๐—˜๐—ป๐˜ƒ๐—ถ๐—ฟ๐—ผ๐—ป๐—บ๐—ฒ๐—ป๐˜

The environment is a representation of the context that our agent will interact with. It can represent an aspect of the real world, like the stock market, or a street for example, or it can be a completely virtual environment, like a game.
๐—ฆ๐˜๐—ฎ๐˜๐—ฒ

States are observations that the agent receives from the environment. It's the way the agent receives all available information about the environment.
๐—”๐—ฐ๐˜๐—ถ๐—ผ๐—ป๐˜€

Actions are performed by the agent and may change the state of the environment. All the rules of how an action changes the state of the environment are internal to the environment. For a given state, the agent can choose which will be its next action ...
... but it does not have any control over how this action will affect the environment.
๐—ฅ๐—ฒ๐˜„๐—ฎ๐—ฟ๐—ฑ๐˜€

Rewards signal to the agent if an action was correct or not.
So, if you want to learn more about Reinforcement Learning by a practical example, take a look at the following blog post:

reinforcement-learning4.fun/2019/06/09/intโ€ฆ

#MachineLearning #ArtificialIntelligence

โ€ข โ€ข โ€ข

Missing some Tweet in this thread? You can try to force a refresh
ใ€€

Keep Current with Rodolfo Mendes ๐Ÿ‡ง๐Ÿ‡ท

Rodolfo Mendes ๐Ÿ‡ง๐Ÿ‡ท Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @rodolfo_mmendes

8 Jun
Machine Learning Applications: Topic Discovery with Clustering

Given a set of documents, a common task is to group them accordingly to topics or common subjects. A human agent can create a hierarchy of subjects and assign each document to its corresponding topic.
However, a clustering algorithm can create this structure automatically and more precisely. We can apply hierarchical clustering algorithms to group similar documents as we build the hierarchy between them.
We don't need to set the subjects nor the topic hierarchy previously. Instead, they are discovered as we perform the clustering.
Read 5 tweets
26 May
Machine Learning Thread: Exploratory Data Analysis

For me, exploratory data analysis is the most challenging task when building a machine learning model, especially for beginners.

(1/n)
A result of the No-Free-Lunch-Theorem is that there's no single model that will perform well for every dataset. In other words, there's no silver bullet Machine Learning Algorithm.

(2/n)
The practical consequence is that we need to make a LOT of human decisions when building our model: which algorithm to use, which features to use, which features to discard, apply normalization, regularization, hyperparameters to tune.

(3/n)
Read 6 tweets
26 May
Machine Learning Applications: Stroke Prediction

The Stroke Prediction Dataset @kaggle is an example of how Machine Learning can be used for disease prediction.

kaggle.com/fedesoriano/stโ€ฆ
The dataset comprises more than 5,000 observations of 12 attributes representing clinical conditions of patients like heart disease, hypertension, glucose, smoking, and others. For each observation, there's also a binary target variable indicating if a patient had a stroke.
By training typical classification algorithms like logistic regression, KNN, SVM classifiers, decision trees, or others, we can build a model to predict the stroke.
Read 5 tweets
25 May
Machine Learning Applications: Medical Diagnosis

An increasing application of machine learning classification algorithms is medical diagnose. Basically, diagnosing if a patient has a specific disease is a simple binary classification problem.

#MachineLearning
For example, we may build a model to identify if a patient has Hepatitis C. In this case, there are 2 possible outputs: yes and no, which is a typical binary classification problem.

#MachineLearning
Thus, the big challenge for medical diagnosis is collecting the right data to train a model for a specific disease: blood tests, x-ray images, ultrasound ... Each one of these types of data can help on diagnosis and need specific treatment before used to feed ML models
Read 5 tweets
24 May
Classification Applications: Spam Detection

Spam detection is one of the classical applications of classification algorithms. It simply consists of assigning a received email one of two labels: spam or not spam.

#MachineLearning
By automatically classifying received emails as spam or not spam, email services provide a cleaner and safer mail Inbox.
The training data is obtained by collecting samples of emails kept in Inbox or archived and emails manually labeled as Spam.
Read 7 tweets
17 May
Machine Learning Applications: Natural Language Processing

Natural Language Processing is the ability of a computer to interpret human language. NLP it's not only about text processing but also about understanding sentences and documents.

#MachineLearning
By giving computers the ability to interpret human language, we can build better human-machine interfaces, extract information from non-structured data, and increment automation.

#MachineLearning
Like Apple's Siri and Amazon's Alexa, virtual assistants are examples of how we can use NLP to build better human-machine interfaces.

Spam detectors are an example of how NLP can automatize the task of keeping our mail boxes clean.
Read 5 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!

:(