OpenAI + Dota 2

We've trained a human-like robot hand to manipulate physical objects with unprecedented dexterity. Our system, called Dactyl, is trained entirely in simulation and transfers its knowledge to reality, adapting to real-world physics using techniques we've been working on for the past year. This system is trained using the learning algorithm and code created for OpenAI Five: https://blog.openai.com/learning-dexterity/ | OpenAI

We’ve developed a hierarchical reinforcement learning algorithm that learns high-level actions useful for solving a range of tasks, allowing fast solving of tasks requiring thousands of timesteps. Our algorithm, when applied to a set of navigation problems, discovers a set of high-level actions for walking and crawling in different directions, which enables the agent to master new navigation tasks quickly. Details: https://blog.openai.com/learning-a-hierarchy/ Code: https://github.com/openai/mls