BarclayII

#!/usr/bin/env python

"""
Code to load an expert policy and generate roll-out data for behavioral cloning.
Example usage:
    python run_expert.py experts/Humanoid-v1.pkl Humanoid-v1 --render \
            --num_rollouts 20

Author of this script and included expert policies: Jonathan Ho (hoj@openai.com)
"""

BarclayII

import argparse
import mxnet as mx
from mxnet import nn
from mxnet.contrib import autograd
import numpy as np
import time
import os

ngpu = 1
nz = 100

BarclayII

import tensorflow as TF
import modeltf as model

import numpy as NP
import numpy.random as RNG

import h5py

import argparse

BarclayII

import torch as T
import numpy as NP

### Norm of vector difference

# Checker
def normdiff_assert(X, Y, normdiff):
    norm = normdiff(X, Y)
    for i in range(X.size()[2]):

BarclayII

import torch as T
import numpy as np
x = T.autograd.Variable(T.randn(5, 8), requires_grad=True)
p = T.nn.functional.softmax(x)
y = p.multinomial()
y.reinforce(T.ones(y.size()))
y.backward()
d = x.grad.data.clone().numpy()
x.grad.data.zero_()
logp = T.nn.functional.log_softmax(x)

BarclayII

# Modified from example/autograd/{data,dcgan}.py to make it standalone.
import argparse
import mxnet as mx
from mxnet import nn
from mxnet.contrib import autograd
import numpy as np
import matplotlib.pyplot as PL
import time
import os

BarclayII

# References:
# https://arxiv.org/pdf/1405.5869.pdf
# https://arxiv.org/abs/1507.05910

import numpy as np
from scipy.spatial.distance import cosine

# Rescaling and appending new components to "normalize" data vectors
X = np.random.randn(10000, 100)
Xn = np.sqrt((X ** 2).sum(1))

BarclayII

import torch
import time

N = 10000
D = 50
E = 500000
T = 10

t_gather = 0
t_scatter = 0

BarclayII

'''
Original implementation
https://github.com/clab/dynet_tutorial_examples/blob/master/tutorial_parser.ipynb

The code structure and variable names are similar for better reference.

Not for serious business, just for some comparison between PyTorch and DyNet
(and I still prefer PyTorch)
'''
import torch as T

BarclayII

# coding: utf-8
import torch
import time
import pandas as pd
import tqdm

B, L, N, H, W = 64, 50, 10, 256, 3

print('warming up')
for _ in tqdm.trange(10):