ETH Zurich and NVIDIA’s Massively Parallel Deep RL Enables Robots to Learn to Walk in Minutes | Synced
A research team from ETH Zurich and NVIDIA proposes a training framework that enables fast policy generation for real-world robotic tasks — training time can be reduced by multiple orders of magnit...
Source: Synced | AI Technology & Industry Review
A research team from ETH Zurich and NVIDIA proposes a training framework that enables fast policy generation for real-world robotic tasks — training time can be reduced by multiple orders of magnitude using massive parallelism on a single workstation GPU.