karpathy

""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import cPickle as pickle
import gym

# hyperparameters
H = 200 # number of hidden layer neurons
batch_size = 10 # every how many episodes to do a param update?
learning_rate = 1e-4
gamma = 0.99 # discount factor for reward

StanislawAntol

#!/usr/bin/python3

from sys import exit
from sys import stdout
from sys import path as syspath
from os import path as osp
from os import stat, makedirs
import argparse

from shutil import copyfile

tsu-nera

import gym
import numpy as np
from collections import deque
from gym import wrappers

# Create the Cart-Pole game environment
env = gym.make('CartPole-v0')
env = wrappers.Monitor(env, '/tmp/cartpole-experiment-1')

def relu(x):

codebrainz

/*
* one.c -- Lua core, libraries, and interpreter in a single file (Lua 5.3)
*/

/* default is to build the full interpreter */
#ifndef MAKE_LIB
#ifndef MAKE_LUAC
#ifndef MAKE_LUA
#define MAKE_LUA
#endif

cajames

import cdk = require("@aws-cdk/core");
import { Vpc, Port } from "@aws-cdk/aws-ec2";
import {
  Cluster,
  ContainerImage,
  AwsLogDriver,
  FargatePlatformVersion,
  NetworkMode,
  CfnService,
} from "@aws-cdk/aws-ecs";

pahud

import { App, Construct, Stack, StackProps, CfnParameter, CfnCondition, Fn } from '@aws-cdk/core';
import * as sns from '@aws-cdk/aws-sns';

export interface DemoProps { }

export class Demo extends Construct {
  constructor(scope: Construct, id: string) {
    super(scope, id)

    const stack = Stack.of(this);