HenryJia

import numpy as np
import gym

def sigmoid(x):
    return 1.0 / (1.0 + np.exp(-x))

env = gym.make('CartPole-v1')
desired_state = np.array([0, 0, 0, 0])
desired_mask = np.array([0, 0, 1, 0])

HenryJia

import time
import numpy as np
import torch
from lighter.train import AsynchronousLoader
from torch.utils.data import DataLoader

batch_size = 2 ** 13
length = 100
device = torch.device('cuda:0')

HenryJia

import time, os, sys, argparse
import numpy as np # linear algebra 
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
np.random.seed(94103)

import torch
import torch.nn as nn
from torch.optim import Adam
from torch.utils.data import DataLoader

HenryJia

# Based on https://scipy-lectures.org/packages/scikit-learn/auto_examples/plot_tsne.html
# tSNE: https://en.wikipedia.org/wiki/T-distributed_stochastic_neighbor_embedding
# MNIST Dataset: http://yann.lecun.com/exdb/mnist/

import struct

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt