chris-chris

# From udacity Machine Learning Nanodegree course

import numpy as np

# Define sigmoid function
def sigmoid(x):
  return 1/(1+np.exp(-x))

# Derivative of the sigmoid function
def sigmoid_derivative(x):

cbaziotis

from keras import backend as K, initializers, regularizers, constraints
from keras.engine.topology import Layer


def dot_product(x, kernel):
    """
    Wrapper for dot product operation, in order to be compatible with both
    Theano and Tensorflow
    Args:

j-min

benjamintd

# coding: utf-8

# Imports

import os
import cPickle
import numpy as np
import theano
import theano.tensor as T

tambetm

Used dueling network architecture with Q-learning, as outlined in this paper:

Dueling Network Architectures for Deep Reinforcement Learning
Ziyu Wang, Tom Schaul, Matteo Hessel, Hado van Hasselt, Marc Lanctot, Nando de Freitas
http://arxiv.org/abs/1511.06581

Command line:

python duel.py CartPole-v0 --gamma 0.995

rrag

license: MIT
height: 420

ryanflorence

.
├── actions
├── stores
├── views
│   ├── Anonymous
│   │   ├── __tests__
│   │   ├── views
│   │   │   ├── Home
│   │   │   │   ├── __tests__
│   │   │   │   └── Handler.js

kachayev

# Simple:
# a --> b
#   --> c --> d
#   --> d 
graph1 = {
    "a": ["b", "c", "d"],
    "b": [],
    "c": ["d"],
    "d": []
}

andreyvit

tmux cheat sheet

(C-x means ctrl+x, M-x means alt+x)

Prefix key

The default prefix is C-b. If you (or your muscle memory) prefer C-a, you need to add this to ~/.tmux.conf:

remap prefix to Control + a