jojonki

# -*- coding: utf-8 -*-

import gym
from gym import wrappers

env = gym.make("CartPole-v0")
env = wrappers.Monitor(env, './cartpole-experiment-1')
for i_episode in range(20):
    observation = env.reset()
    for t in range(100):

jojonki

# -*- coding: utf-8 -*-
# ref: https://gym.openai.com/evaluations/eval_1lfzNKEHS9GA7nNWE73w

import numpy as np
import gym
from gym import wrappers

# Q learning params
ALPHA = 0.1 # learning rate
GAMMA = 0.99 # reward discount

jojonki

# -*- coding: utf-8 -*-
# ref: http://taotao54321.hatenablog.com/entry/2016/11/08/180245

import numpy as np
import gym
from gym import wrappers

# Q learning params
ALPHA = 0.1 # learning rate
GAMMA = 0.99 # reward discount

jojonki

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

jojonki

'''This script demonstrates how to build a variational autoencoder with Keras.
Reference: "Auto-Encoding Variational Bayes" https://arxiv.org/abs/1312.6114
'''
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import norm

from keras.layers import Input, Dense, Lambda, Layer
from keras.models import Model
from keras import backend as K

jojonki

import random
import torch
import torch.nn as nn
from torch.autograd import Variable
from torch import optim
import torch.nn.functional as F

seq_len = 10
n_class = 5
class SimpleNet(nn.Module):

jojonki

# https://stackoverflow.com/questions/7851077/how-to-return-index-of-a-sorted-list
s = [2, 3, 1, 4, 5]
sorted(range(len(s)), key=lambda k: s[k])
# [2, 0, 1, 3, 4]

sorted(range(len(s)), key=lambda k: s[k], reverse=True)
# [4, 3, 1, 0, 2]

jojonki

jojonki

%load_ext autoreload
%autoreload 2

jojonki

# https://discuss.pytorch.org/t/how-pytorch-releases-variable-garbage/7277/2
def memReport():
    for obj in gc.get_objects():
        if torch.is_tensor(obj) or (hasattr(obj, 'data') and torch.is_tensor(obj.data)):
            print(type(obj), obj.size())
    
def cpuStats():
        print(sys.version)
        print(psutil.cpu_percent())
        print(psutil.virtual_memory())  # physical memory usage