Policy Transfer via Kinematic Domain Randomization and Adaptation
Ioannis Exarchos,Yifeng Jiang,Wenhao Yu,C. Karen Liu,Ioannis Exarchos,Yifeng Jiang,Wenhao Yu,C. Karen Liu
Transferring reinforcement learning policies trained in physics simulation to the real hardware remains a challenge, known as the "sim-to-real" gap. Domain randomization is a simple yet effective technique to address dynamics discrepancies across source and target domains, but its success generally depends on heuristics and trial-and-error. In this work we investigate the impact of randomized para...
