Research at NVIDIA: GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning

To help make training more accessible, a team of researchers from NVIDIA and Carnegie Mellon University developed a GPU-accelerated reinforcement learning simulator that can teach a virtual robot human-like tasks in record time: https://nvda.ws/2AB7a7t https://ift.tt/2RsfdJ9 NVIDIA October 31, 2018 at 04:37PM