Reinforcement Learning
A series of tutorials on reinforcement learning, mainly for robotics applications.
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
A series of tutorials on reinforcement learning, mainly for robotics applications.
A non-exhaustive list of definitions of data science terms.
Learn about deep neural networks, starting from the basics.
A blog series is about optimisation, including evolutionary optimisation and Bayesian optimisation.
Learn to use supervised learning for classification and regression problems
A number of handy cheat sheets to remember commands and syntax for various programming tools.
A review of the different anomaly detection approaches for time series data.
The person behind the scene.
Some general rules to leave a comment via Disqus
Privacy policy and terms and conditions.
Page not found. Your pixels are in another canvas.
Some useful commands and shortcuts for the Vim text editor
Some useful commands and shortcuts for ROS
Some useful syntax for the Markdown format
Some useful commands and shortcuts for the Linux Bash command line interpreter
Some useful commands and shortcuts for the Git version-control system
Some useful commands and shortcuts for Docker
Some useful commands and shortcuts for Conda
A comparison of some popular optimisation frameworks
Understand how genetic algorithms work and implement a simple one in Python
A non-exhaustive list of optimisation algorithms, classed by categories.
A step-by-step instructions to install Tensorflow2 with GPU support on Ubuntu
Installing TensorFlow with GPU support on Ubuntu can be troublesome. We will see how to use Docker avoid a headache.
A simple classification example with Keras.
A simple classification example with Pytorch.
Learn to solve a multi-class classification problem with neural networks in Python.
Let’s see how to deal with non-linear classification problems with artificial neural networks.
Implement a simple artificial neural network from scratch using only the Numpy library.
We explain the concept behind the backpropagation algorithm with the multi-layer perceptron
In this post, we will explain how simple artificial neural networks works
Let’s compare some reinforcement learning libraries
I implemented some custom Gym environments for robotics applications with Pybullet and ROS.
An introduction to Pybullet, an open-source physics engine simulator for robotics.
Implement the 4 methods for the tic-tac-toe Gym environment.
Learn to create and register a minimal custom Gym environment.
Learn to implement your own training environments with the Gym library.
Understand how DQN works and appy it to the Cartpole problem.
Adapting Q learning to solve continuous state problems.
Q learning is a simple and efficient way to solve discrete state problems.
Learn to initialise virtual environments for training RL agents with the OpenAI Gym library and implement simple policies.
Some interesting research projects that apply reinforcement learning to robotics
A list of popular reinforcement learning algorithms grouped by category
An introduction to the main concepts of reinforcement learning