now loading...
: Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning
: The paper describes a method using NVIDIA Isaac Gym and deep reinforcement learning to train legged robots in a simulation that is so fast and accurate that the robot can "learn" complex locomotion in minutes of real-world time. Why this file name is famous
: Jemin Hwangbo, Joonho Lee, Alexey Dosovitskiy, Dario Bellicoso, Vassilios Tsounis, Vladlen Koltun, and Marco Hutter.
The video specifically showcases the robot (developed by ANYbotics and ETH Zurich) learning to walk and recover from falls in a simulated environment before being deployed to the real world. Paper Details
: Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning
: The paper describes a method using NVIDIA Isaac Gym and deep reinforcement learning to train legged robots in a simulation that is so fast and accurate that the robot can "learn" complex locomotion in minutes of real-world time. Why this file name is famous 1641004453409.webm
: Jemin Hwangbo, Joonho Lee, Alexey Dosovitskiy, Dario Bellicoso, Vassilios Tsounis, Vladlen Koltun, and Marco Hutter. : Learning to Walk in Minutes Using Massively
The video specifically showcases the robot (developed by ANYbotics and ETH Zurich) learning to walk and recover from falls in a simulated environment before being deployed to the real world. Paper Details 1641004453409.webm