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. 

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

Google's DeepMind AI Just Taught Itself To Walk

CGVR Lab - Thesis Fullscreen Viewer

Applied Sciences, Free Full-Text

Last Week in AI on Apple Podcasts

Scaling up learning across many different robot types - Google

PDF) Artificial Intelligence Driven Non-Linear Narrative: An

Deep reinforcement learning for real-world quadrupedal locomotion

Reinforcement Learning – Silverton Consulting

New method uses crowdsourced feedback to train robots - Essentials

PDF) Robot's play: interactive games with sociable machines.

DeepMind Builds AI That Reconstructs 3D Objects From a Single

Reinforcement learning, teaching robots new tricks

PDF) Sim-to-Real Robot Learning from Pixels with Progressive Nets

Last Week in AI a podcast by Skynet Today