16 lines
479 B
Python
16 lines
479 B
Python
|
import datetime
|
||
|
|
from typing import NamedTuple, Optional
|
||
|
|
|
||
|
|
|
||
|
|
class PPOConfig(NamedTuple):
|
||
|
|
NNShape: list = [256, 256, 128]
|
||
|
|
actorLR: float = 2e-3 # Actor Net Learning
|
||
|
|
criticLR: float = 2e-3 # Critic Net Learning
|
||
|
|
gamma: float = 0.99
|
||
|
|
lmbda: float = 0.95
|
||
|
|
clipRange: float = 0.20
|
||
|
|
entropyWeight: float = 1e-2
|
||
|
|
trainEpochs: int = 8
|
||
|
|
saveDir: str = "PPO-Model/" + datetime.datetime.now().strftime("%m%d-%H%M") + "/"
|
||
|
|
loadModelDir: Optional[str] = None
|