Augmented Random Search (ARS)

Augmented random search (ARS)is a model-free reinforcement learning, and a modified basic random search (BRS) algorithm, the algorithm was first published in 2018 by the trio - Horia Mania, Aurelia Guy, and Benjamin Recht from the University of California, Berkeley. When ARS is compared with other AI algorithms, it is 15 times faster and more efficiecnt, returning higher rewards when applied to a specific application, like the locomotion task in MuJoCo (Multi-Joint Dynamics with Contact) environ...