Get started with deep reinforcement learning by training agents to play Volleyball. — Purpose If you’re new to reinforcement learning (RL), there’s some great introductory courses out there. Just to name a few: Introduction to Reinforcement Learning by David Silver Spinning Up by OpenAI Reinforcement Learning Specialization by University of Alberta But if you’re anything like me, you might prefer a ‘learning by doing’…

A guide to choosing the right tools for your business or career — There are dozens of data analysis tools out there, with each being designed with a certain use case in mind. Sometimes, tools overlap and serve the same use cases and both have their pros & cons. This can make it challenging for finding the right tools for your needs. Today…

How close are we to seeing reinforcement learning in our everyday lives? Here are examples of real-world use cases for reinforcement learning — from robotics to personalizing your Netflix recommendations. — Reinforcement learning is a subdomain of machine learning in which agents learn to make decisions by interacting with their environment. It recently gained popularity through its ability to achieve superhuman-levels of play in games like Go, Chess, Dota, and StarCraft II.

Looking for a way to get practical, hands-on experience with reinforcement learning? Here are some project ideas to inspire you. — This post is a compilation of reinforcement learning (RL) project ideas to check out. I’ve tried to select projects covering a range of different difficulties, concepts, and algorithms in RL. 1. Solve toy problems with OpenAI Gym (beginner-friendly) OpenAI Gym has become the de facto standard for reinforcement learning frameworks among researchers and practitioners. Solving toy problems from…

Coder One (formerly the AI Sports Challenge) is an online AI programming competition for engineers, data scientists, researchers, students, and hobbyist programmers. The event is supported by our community partners SitePoint, General Assembly, Hackathons Australia, and the Data Science and AI Association of Australia (DSAi) (thank you!). Whether this is…

Where do you go to ask questions and meet others studying machine learning? Here’s a curated up-to-date list of helpful and active communities to check out. — At some point during your machine learning journey you may get stuck on a problem, start to lose motivation, or find yourself unable to keep up the rapid rate of new developments. In these situations, I find communities have a lot to offer regardless of your skill level.

A list of ongoing and annual competitions suitable for getting hands-on practice with reinforcement learning (while winning a prize or two). — Reinforcement learning (RL) is a subdomain of machine learning which involves agents learning to make decisions by interacting with their environment. While popular competition platforms like Kaggle are mainly suited for supervised learning problems, RL competitions are harder to come by.

Train agents to play volleyball using self-play in Unity ML Agents. — An overview of self-play Competitive self-play involves training an agent against itself. It was used in famous systems such as AlphaGo and OpenAI Five (Dota 2). By playing increasingly stronger versions of itself, agents can discover new and better strategies. In this post, we walk through using competitive self-play in Unity ML-Agents to train…

How to train agents to play volleyball using deep reinforcement learning. — This article is part 4 of the series ‘A hands-on introduction to deep reinforcement learning using Unity ML-Agents’. It’s also suitable for anyone interested in using Unity ML-Agents for their own reinforcement learning project. Recap and overview In parts 2 and 3, we built a volleyball environment using Unity ML-Agents. To recap, here…