Sim-to-Real Policy and Reward Transfer with Adaptive Forward Dynamics Model
Rongshun Juan,Hao Ju,Jie Huang,Randy Gomez,Keisuke Nakamura,Guangliang Li,Rongshun Juan,Hao Ju,Jie Huang,Randy Gomez,Keisuke Nakamura,Guangliang Li
Deep reinforcement learning has shown promise in learning robust skills for robot control, but typically requires a large amount of samples to achieve good performance. Sim-to-real transfer learning has been developed to solve this problem, but the policy trained in simulation usually has unsatisfactory performance in the real world because simulators inevitably model the dynamics of reality imper...
