domluna

def conv2d(inputs, filter, strides, name='conv2d'):
        k = tf.get_variable('W', filter, initializer=xavier_initializer_conv2d())
        b = tf.get_variable('b', filter[-1], initializer=tf.constant_initializer(0.0))
        conv = tf.nn.conv2d(inputs, k, strides, 'SAME')
        bias_add = tf.nn.bias_add(conv, b)
        return tf.nn.relu(bias_add, name=name)


def vision_model(frames, n_frames):
    with tf.variable_scope('Conv1') as scope:

domluna

Run with defaults

python vpg.py

domluna

# User configuration
export PATH="$HOME/.linuxbrew/bin:$PATH"
export MANPATH="$HOME/.linuxbrew/share/man:$MANPATH"
export INFOPATH="$HOME/.linuxbrew/share/info:$INFOPATH"

# add cuda tools to command path
export PATH=/usr/local/cuda/bin:${PATH}
export MANPATH=/usr/local/cuda/man:${MANPATH}

# add cuda libraries to library path

domluna

To replicate run

python cem.py --algorithm pcem --outdir CartPole-v0-pcem

The --outdir argument is optional. If left as is results will be written to /tmp/CartPole-v0-pcem.

domluna

Implements the Cross-Entropy Method with decreasing noise added to the variance updates as described in [1].

Running cem.py with the default settings should reproduce results.

[1] Szita, Lorincz 2006 
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.81.6579&rep=rep1&type=pdf

domluna

{
  "parser": "babel-eslint",
  "env": {
    "node": true,
    "mocha": true
  },
  "rules": {
    "brace-style": 2,
    "camelcase": 2,
    "comma-dangle": [2, "never"],

domluna

Some questions to ask during interviews:

* What does success look like for this position? How will I know if I am accomplishing what is expected of me?
* What is the last project you shipped? What was the goal, how long did it take, what were the stumbling blocks, what tools did you use, etc.
* What will my first 90 days in this role look like? First 180 days?
* Who will I report to and how many people report to that person? Do they have regular 1:1 with their team members?
* Why did the last person who quit this team leave? The company?
* If a startup, how long is your runway? How are financial decisions made?
* What would be my first project here? Has someone already been working on this or is this in the aspirational stage?
* What is the current state of the data infrastructure? How much work needs to be done on getting the infrastructure and pipeline into shape before we start analyzing that data?

domluna

" General
set encoding=utf-8
set fileencoding=utf-8
" Match and Search
set ignorecase
set smartcase
set hlsearch
set incsearch
" set autochdir
set tabstop=4

domluna

from __future__ import print_function
from scrapy.selector import Selector
import requests

def scrape_comments(url):
    comments = []
    r = requests.get(url).text
    sel = Selector(text=r)

    rough_comments = sel.xpath("//span[@class='comment']/span")

domluna

from __future__ import print_function, absolute_import
import cgt
from cgt import nn
from cgt.distributions import categorical
import numpy as np
from load import load_mnist
import time

epochs = 10
batch_size = 128