DeepMind UniSim simulates reality to train robots, game characters

UniSim can also simulate rare events, a feature that is particularly useful in robotics and self-driving car applications, where data collection can be costly and risky. 

Artificial Intelligence News

Artificial Intelligence & Deep Learning

DeepMind teaches mini-robots to play football - digitec

Speeding Up Reinforcement Learning with a New Physics Simulation

iGibson: A Simulation Environment to Train AI Agents in Large

DeepMind's UniSim: a universal simulator that brings together data

Reinforcement learning algorithms: A brief survey - ScienceDirect

Deep reinforcement learning for real-world quadrupedal locomotion

Train your robots like video game characters! Real World Simulators?

Talking to Robots in Real Time – Google Research Blog

Reinforcement Learning – Silverton Consulting

Humanoid Robots Learn To Play Soccer Using Google's DeepMind AI

Opinion A.I. Could Solve Some of Humanity's Hardest Problems. It