Gaussian Policy

class rlforge.policies.gaussian(mu, sigma)

Sample an action from a Gaussian (normal) distribution.

This policy is typically used in environments with continuous action spaces, where actions are drawn from a distribution parameterized by mean (mu) and standard deviation (sigma).

Parameters

mufloat

Mean of the Gaussian distribution.

sigmafloat

Standard deviation of the Gaussian distribution.

Returns

actionfloat

A real-valued action sampled from N(mu, sigma^2).