no code implementations • 25 Oct 2023 • Kelin Yu, Yunhai Han, Matthew Zhu, Ye Zhao
To further mitigate the embodiment gap between humans and robots, we employ online residual reinforcement learning on the physical robot.
no code implementations • 15 Jun 2023 • Max Asselmeier, Zhaoyi Li, Kelin Yu, Danfei Xu
Additionally, an evolutionary training environment generates all the curriculum to improve the DRL model's inadequate skills tested in the previous evaluation.