if __name__ == "__main__":
# import grid2op
import numpy as np
from grid2op.Parameters import Parameters
from grid2op import make
from grid2op.Reward import BaseReward
from grid2op.dtypes import dt_float
import re
try:
from lightsim2grid.LightSimBackend import LightSimBackend
backend = LightSimBackend()
except:
from grid2op.Backend import PandaPowerBackend
backend = PandaPowerBackend()
args = cli_train().parse_args()
# is it highly recommended to modify the reward depening on the algorithm.
# for example here i will push my algorithm to learn that plyaing illegal or ambiguous action is bad
class MyReward(BaseReward):
power_rho = int(4) # to which "power" is put the rho values
penalty_powerline_disco = 1.0 # how to penalize the powerline disconnected that can be reconnected
# how to penalize the fact that a powerline will be disconnected next time steps, because it's close to
# an overflow
penalty_powerline_close_disco = 1.0
# cap the minimum reward (put None to ignore)
cap_min = -0.5 # if the minimum reward is too low, model will not learn easily. It will be "scared" to take
# actions. Because you win more or less points 1 by 1, but you can lose them
kwargs:
Other key-word arguments that you might use for training.
"""
baseline = Template(env.action_space, env.observation_space, name=name)
if load_path is not None:
baseline.load(load_path)
baseline.train(env, iterations, save_path)
# as in our example (and in our explanation) we recommend to save the mode regurlarly in the "train" function
# it is not necessary to save it again here. But if you chose not to follow these advice, it is more than
# recommended to save the "baseline" at the end of this function with:
# baseline.save(path_save)
if __name__ == "__main__":
"""
This is a possible implementation of the train script.
"""
import grid2op
from l2rpn_baselines.utils import cli_train
args_cli = cli_train().parse_args()
env = grid2op.make()
train(env=env,
name=args_cli.name,
iterations=args_cli.num_train_steps,
save_path=args_cli.save_path,
load_path=args_cli.load_path)