Deep Reinforcement learning is used to program humanoid robots to play agile soccer.

Deep reinforcement learning for bipedal robots to learn agile soccer skills
Researchers from Google’s DeepMind AI Lab have programmed two little humanoid robotic robots to play the classic game of one-versus-1 soccer. The results are adorable.

We studied the application of Deep Reinforcement Learning for 1v1 soccer using the Robotis OP3 mini humanoid robot.

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

Source:

发表回复

您的电子邮箱地址不会被公开。 必填项已用 * 标注