Nanjing University’s LAMDA team developed Marope, a multi-agent reinforcement learning framework that allows two robots to coordinate the rope while adapting to the jumper’s rhythm in real time.
Paper: https://t.co/53crYo5eEz
Demo: https://t.co/yBbdeLwjHp
RL bros and sisters, check this crazy repo out...
Nvidia's open source framework to train physics-based humanoid controllers... Learning from mocap data, reinforcement learning, procedural terrain/obstacle generation... Just an insane amount of stuff! Awesome!