Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

set_seed in helpers #88

Merged
merged 1 commit into from
Oct 16, 2023
Merged

set_seed in helpers #88

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions cares_reinforcement_learning/util/helpers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,16 @@
import torch
import numpy as np
import random

import pandas as pd
import matplotlib.pyplot as plt

def set_seed(seed):
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
np.random.seed(seed)
random.seed(seed)


def plot_reward_curve(data_reward):
data = pd.DataFrame.from_dict(data_reward)
Expand Down
8 changes: 2 additions & 6 deletions example/example_training_loops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
from cares_reinforcement_learning.util import Record
from cares_reinforcement_learning.util import EnvironmentFactory
from cares_reinforcement_learning.util import arguement_parser as ap
from cares_reinforcement_learning.util import helpers as hlp

import cares_reinforcement_learning.train_loops.policy_loop as pbe
import cares_reinforcement_learning.train_loops.value_loop as vbe
Expand All @@ -22,11 +23,6 @@
from pathlib import Path
from datetime import datetime

def set_seed(seed):
torch.manual_seed(seed)
np.random.seed(seed)
random.seed(seed)

def main():
parser = ap.create_parser()
args = vars(parser.parse_args()) # converts to a dictionary
Expand All @@ -53,7 +49,7 @@ def main():
training_iterations = args['number_training_iterations']
for training_iteration in range(0, training_iterations):
logging.info(f"Training iteration {training_iteration+1}/{training_iterations} with Seed: {args['seed']}")
set_seed(args['seed'])
hlp.set_seed(args['seed'])
env.set_seed(args['seed'])

logging.info(f"Algorithm: {args['algorithm']}")
Expand Down