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

odashi

#include <iomanip>
#include <iostream>
#include <cstdlib>
#include <vector>

#include <cuda.h>
#include <cudnn.h>

#define CUDA_CALL(f) { \
  cudaError_t err = (f); \

kittinan

import cv2
import io
import socket
import struct
import time
import pickle
import zlib

client_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
client_socket.connect(('192.168.1.124', 8485))

ShichengChen

#include <iostream>
#include <algorithm>
#include <set>
#include <vector>
#include <cstring>
#include <queue>
#include <bits/stdc++.h>
#include <cstdio>
#include <stdio.h>
using namespace std;

ShichengChen

#define debug(x) cout << '>' << #x << ':' << (x) << endl;
#define debug2(y,z) cout << '>' << #y << ':' << (y) << " " << #z << ":" <<(z) << endl;

bougui505

#!/usr/bin/env python
# -*- coding: UTF8 -*-

# Author: Guillaume Bouvier -- [email protected]
# https://research.pasteur.fr/en/member/guillaume-bouvier/
# 2020-10-01 09:51:45 (UTC+0200)

import sys
import torch

ShichengChen

#include <bits/stdc++.h>
#include<ext/pb_ds/assoc_container.hpp>
typedef long long ll;
using namespace std;
using namespace __gnu_pbds;
#define lcnt (cnt<<1)
#define rcnt (cnt<<1|1)
#define vt vector
#define pb push_back
#define all(c) (c).begin(), (c).end()