Skip to content

Instantly share code, notes, and snippets.

View ex4sperans's full-sized avatar

Dmytro Danevskyi ex4sperans

View GitHub Profile
import numpy as np
n = 100
k = 10000
clip_value = 3
p_cheat = 0.5
def generate_test_results():
import time
import gym
import numpy as np
import tensorflow as tf
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('--gamma', type=float, default=0.995, help='a discount factor')
parser.add_argument('--num_iter', type=int, default=1000, help='maximum number of iterations')