ornstein-uhlenbeck
In mathematics, the Ornstein–Uhlenbeck process is a stochastic process with applications in financial mathematics and the physical sciences. Its original application in physics was as a model for the velocity of a massive Brownian particle under the influence of friction. It is named after Leonard Ornstein and George Eugene Uhlenbeck. [1]
The samples generated in this process are often used in reinforcement learning for exploration, for example in deep mind's ddpg. [2]
The implementation is inspired by [3].
use OrnsteinUhlenbeckProcessBuilder;
use ;
const ACTION_MIN: f64 = -0.5;
const ACTION_MAX: f64 = 0.5;
let mut ou_process = default.build;
for step in 0..100
License: Apache-2.0/MIT