OpenAI announces educational resource 'Spinning Up' for anyone to learn skills of deep level reinforcement learning

In order to understand AI technology it is necessary to acquire knowledge of machine learning, especially to be able to understand and utilize deep level reinforcement learning is essential. OpenAI , a nonprofit organization that studies artificial intelligence founded by Mr. Eulon Mask et al., Has an educational resource " Spinning Up " for students to learn deep level reinforcement learning so that anyone can become a practitioner released.

Spinning Up in Deep RL
https://blog.openai.com/spinning-up-in-deep-rl/

OpenAI established by Mr. Ellon Mask and others such as Tesla · SpaceX etc. and Sam Oltmann of Y Combatora aims AI to be used in a useful way without harming humanity. Such OpenAI's announced Spinning Up contains clear sample code, practice questions, bibliography, tutorials, and so on.

Machine learning is not necessarily a low hurdle of learning. However, based on the achievements in OpenAI's scholarship program and fellow program , OpenAI believes that even if novice beginners can use deep reinforcement learning in a short time, even if proper guidance and educational resources are in place about. Spinning Up is a resource created based on this idea and is also integrated into the 2019 Winter Scholars Application Open curriculum starting in January 2019 .

Welcome to Spinning Up in Deep RL! - Spinning Up documentation
https://spinningup.openai.com/en/latest/

Spinning Up said that the following five are made as core components.

1. Introduction on reinforcement learning terminology, algorithm type, basic theory
2. Essay on becoming a role in reinforcement learning research field through learning
3. List of important papers summarized by topic
Four. Source code repositories for implementing the following learning enhancement methods: "Vanilla Policy Gradient (VPG)" "Trust Region Policy Optimization (TRPO)" "Proximal Policy Optimization (PPO)" "Deep Deterministic Policy Gradient (DDPG)" "Twin Delayed DDPG (TD 3) "" Soft Actor-Critic (SAC) "
Five. Exercise for light warm-up

Although the contents of Spinning Up are all in English, it seems that it is worthwhile for people interested to work hard to understand machine learning as it was written in plainly easy to read sketches.