Model-based Domain Randomization of Dynamics System with Deep Bayesian Locally Linear Embedding
J. Hyeon Park,Sungyong Park,H. Jin Kim,J. Hyeon Park,Sungyong Park,H. Jin Kim
Domain randomization (DR) is a powerful tool to make a policy robust to the uncertainty of dynamics caused by unobservable environmental parameters. Conventional DR has adopted model-free reinforcement learning as a policy optimizer. However, the model-free methods in DR demand high time-complexity due to the randomization process where the environment is extremely changed. In this paper, we intro...
