How This Robot Taught Itself To Walk In Just A Few Hours

image
  • Researchers affiliated with Google Robotics have successfully managed to get a robot to teach itself without relying on simulation trials.
  • Using deep reinforcement learning, a type of machine learning that borrows from concepts used in psychology, the scientists could avoid hard-programming every walking-related command as well as avoid simulation tests.
  • While the field of self-taught robotic locomotion is still nascent, this work provides sufficient evidence that it works. The team's results were published to arXiv.

Comments

Popular posts from this blog

COVID-19 and Computer Security, Part 1: Telecommuting Risks

Elon Musk Fears He Will Die Before Humans Reach Mars, As Space Innovation Is Very Slow

Sonos Is Canning Its Speaker-Killing 'Recycle Mode'