schola.scripts.sb3.launch.SACSettings

class schola.scripts.sb3.launch.SACSettings(learning_rate: float = 0.0003, buffer_size: int = 1000000, learning_starts: int = 100, batch_size: int = 256, tau: float = 0.005, gamma: float = 0.99, train_freq: int = 1, gradient_steps: int = 1, action_noise: <built-in function any> = None, replay_buffer_class: <built-in function any> = None, replay_buffer_kwargs: dict = None, optimize_memory_usage: bool = False, ent_coef: <built-in function any> = ‘auto’, target_update_interval: int = 1, target_entropy: <built-in function any> = ‘auto’, use_sde: bool = False, sde_sample_freq: int = -1)[source]

Bases: object

Methods

__init__([learning_rate, buffer_size, …])

Attributes

action_noise
batch_size
buffer_size
constructor
critic_type
ent_coef
gamma
gradient_steps
learning_rate
learning_starts
name
optimize_memory_usage
replay_buffer_class
replay_buffer_kwargs
sde_sample_freq
target_entropy
target_update_interval
tau
train_freq
use_sde

Parameters:

• learning_rate (float)

• buffer_size (int)

• learning_starts (int)

• batch_size (int)

• tau (float)

• gamma (float)

• train_freq (int)

• gradient_steps (int)

• action_noise (any)

• replay_buffer_class (any)

• replay_buffer_kwargs (dict)

• optimize_memory_usage (bool)

• ent_coef (any)

• target_update_interval (int)

• target_entropy (any)

• use_sde (bool)

• sde_sample_freq (int)

__init__(learning_rate=0.0003, buffer_size=1000000, learning_starts=100, batch_size=256, tau=0.005, gamma=0.99, train_freq=1, gradient_steps=1, action_noise=None, replay_buffer_class=None, replay_buffer_kwargs=None, optimize_memory_usage=False, ent_coef=‘auto’, target_update_interval=1, target_entropy=‘auto’, use_sde=False, sde_sample_freq=-1)

Parameters:

• learning_rate (float)

• buffer_size (int)

• learning_starts (int)

• batch_size (int)

• tau (float)

• gamma (float)

• train_freq (int)

• gradient_steps (int)

• action_noise (any | None)

• replay_buffer_class (any | None)

• replay_buffer_kwargs (dict | None)

• optimize_memory_usage (bool)

• ent_coef (any)

• target_update_interval (int)

• target_entropy (any)

• use_sde (bool)

• sde_sample_freq (int)

Return type:

None

action_noise: any = None

batch_size: int = 256

buffer_size: int = 1000000

property constructor: Type[SAC]

property critic_type: str

ent_coef: any = ‘auto’

gamma: float = 0.99

gradient_steps: int = 1

learning_rate: float = 0.0003

learning_starts: int = 100

property name: str

optimize_memory_usage: bool = False

replay_buffer_class: any = None

replay_buffer_kwargs: dict = None

sde_sample_freq: int = -1

target_entropy: any = ‘auto’

target_update_interval: int = 1

tau: float = 0.005

train_freq: int = 1

use_sde: bool = False