schola.scripts.sb3.launch.PPOSettings

class schola.scripts.sb3.launch.PPOSettings(learning_rate: float = 0.0003, n_steps: int = 2048, batch_size: int = 64, n_epochs: int = 10, gamma: float = 0.99, gae_lambda: float = 0.95, clip_range: float = 0.2, normalize_advantage: bool = True, ent_coef: float = 0.0, vf_coef: float = 0.5, max_grad_norm: float = 0.5, use_sde: bool = False, sde_sample_freq: int = -1)[source]

Bases: object

Methods

__init__([learning_rate, n_steps, …])

Attributes

batch_size
clip_range
constructor
critic_type
ent_coef
gae_lambda
gamma
learning_rate
max_grad_norm
n_epochs
n_steps
name
normalize_advantage
sde_sample_freq
use_sde
vf_coef

Parameters:

• learning_rate (float)

• n_steps (int)

• batch_size (int)

• n_epochs (int)

• gamma (float)

• gae_lambda (float)

• clip_range (float)

• normalize_advantage (bool)

• ent_coef (float)

• vf_coef (float)

• max_grad_norm (float)

• use_sde (bool)

• sde_sample_freq (int)

__init__(learning_rate=0.0003, n_steps=2048, batch_size=64, n_epochs=10, gamma=0.99, gae_lambda=0.95, clip_range=0.2, normalize_advantage=True, ent_coef=0.0, vf_coef=0.5, max_grad_norm=0.5, use_sde=False, sde_sample_freq=-1)

Parameters:

• learning_rate (float)

• n_steps (int)

• batch_size (int)

• n_epochs (int)

• gamma (float)

• gae_lambda (float)

• clip_range (float)

• normalize_advantage (bool)

• ent_coef (float)

• vf_coef (float)

• max_grad_norm (float)

• use_sde (bool)

• sde_sample_freq (int)

Return type:

None

batch_size: int = 64

clip_range: float = 0.2

property constructor: Type[PPO]

property critic_type: str

ent_coef: float = 0.0

gae_lambda: float = 0.95

gamma: float = 0.99

learning_rate: float = 0.0003

max_grad_norm: float = 0.5

n_epochs: int = 10

n_steps: int = 2048

property name: str

normalize_advantage: bool = True

sde_sample_freq: int = -1

use_sde: bool = False

vf_coef: float = 0.5