memorax.algorithms.SACConfig

class memorax.algorithms.SACConfig

Bases: object

SACConfig(num_envs: int, gamma: float, tau: float, train_frequency: int, target_update_frequency: int, target_entropy_scale: float, gradient_steps: int = 1, burn_in_length: int = 0)

num_envs: int

gamma: float

tau: float

train_frequency: int

target_update_frequency: int

target_entropy_scale: float

gradient_steps: int = 1

burn_in_length: int = 0

__init__(num_envs, gamma, tau, train_frequency, target_update_frequency, target_entropy_scale, gradient_steps=1, burn_in_length=0)

Parameters:

• num_envs (int)

• gamma (float)

• tau (float)

• train_frequency (int)

• target_update_frequency (int)

• target_entropy_scale (float)

• gradient_steps (int)

• burn_in_length (int)

Return type:

None

replace(**updates)

Returns a new object replacing the specified fields with new values.