Koha9
2a498f18f6
add GAIL GAILMem GAILConfig Class. add HumanAction record to save expert data. add tackState future for stack multiple states to let agent knows what happened before.
25 lines
646 B
Python
25 lines
646 B
Python
import datetime
|
|
from typing import NamedTuple
|
|
|
|
from PPOConfig import PPOConfig
|
|
|
|
|
|
class GAILConfig(NamedTuple):
|
|
discrimNNShape: list = [128, 64]
|
|
discrimLR: float = 1e-3
|
|
discrimTrainEpochs: int = 8
|
|
discrimSaveDir: str = "GAIL-Model/" + datetime.datetime.now().strftime("%m%d-%H%M") + "/"
|
|
|
|
ppoConfig: PPOConfig = PPOConfig(
|
|
NNShape=[128, 64],
|
|
actorLR=2e-3,
|
|
criticLR=2e-3,
|
|
gamma=0.99,
|
|
lmbda=0.95,
|
|
clipRange=0.20,
|
|
entropyWeight=1e-2,
|
|
trainEpochs=8,
|
|
saveDir="GAIL-Model/" + datetime.datetime.now().strftime("%m%d-%H%M") + "/",
|
|
loadModelDir=None,
|
|
)
|