Menu

Blog

Jun 17, 2023

Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning

Posted by in category: robotics/AI

A team of researchers from Google’s DeepMind AI lab have programmed a pair of little humanoid robots to play a classic match of one-versus-one soccer — and the results are absolutely adorable.


We investigated the application of Deep Reinforcement Learning (Deep RL) for one-versus-one (1v1) soccer on the Robotis OP3 miniature humanoid robot.

Website: https://sites.google.com/view/op3-soccer.
Paper: https://arxiv.org/abs/2304.13653.

1

Comment — comments are now closed.


  1. DougSpace says:

    And then some government somewhere figures that they had better use this approach to training low-cost robotic combatants. And then other governments figure that they had better not be left behind. And then you have Terminator.

    Thanks Google DeepMind for developing and putting out there the information needed to destroy us all. You helped bring us one step closer!