DeepMind’s Progress Over The Years In Robotics

AI Research Lab DeepMind acquired and open-sourced MuJoCo, a rich and effective contact model. By open-sourcing Multi-Joint Dynamics with Contact (MuJoCo), DeepMind has given a major push to its robotics ambition. This article will trace how DeepMind has been making consistent efforts in pushing the envelope in robotics. Deep reinforcement learning to training robots In 2016, DeepMind researchers demonstrated how deep reinforcement learning can train real physical robots. The paper showed that deep Q-functions-based reinforcement learning algorithms can scale to complex 3D manipulation tasks and efficiently learn deep neural network policies. The authors further showed that the time to train the robots can be further reduced by algorithm parallelisation across multiple robots that