carlos-aguayo

import gym
import pandas as pd
import numpy as np
import random

# https://gym.openai.com/envs/CartPole-v0
# Carlos Aguayo - carlos.aguayo@gmail.com


class QLearner(object):

carlos-aguayo

# https://github.com/suragnair/alpha-zero-general/blob/5156c7fd1d2f3e5fefe732a4b2e0ffc5b272f819/MCTS.py#L105-L121
cur_best = -float('inf')
best_act = -1

# pick the action with the highest upper confidence bound
for a in range(self.game.getActionSize()):
    if valids[a]:
        if (s, a) in self.Qsa:
            u = self.Qsa[(s, a)] + self.args.cpuct * self.Ps[s][a] * math.sqrt(self.Ns[s]) / (
                    1 + self.Nsa[(s, a)])

carlos-aguayo

# https://github.com/suragnair/alpha-zero-general/blob/5156c7fd1d2f3e5fefe732a4b2e0ffc5b272f819/MCTS.py#L37-L48

for i in range(self.args.numMCTSSims):  # self.args.numMCTSSims, the number of MCTS simulations to compute
    self.search(canonicalBoard)  # "search" is a MCTS simulations

s = self.game.stringRepresentation(canonicalBoard)
# Count how many times we have visited each node
counts = [self.Nsa[(s, a)] if (s, a) in self.Nsa else 0 for a in range(self.game.getActionSize())]

if temp == 0:

carlos-aguayo

__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_1 (InputLayer)            (None, None, None, 3 0                                            
__________________________________________________________________________________________________
conv2d_1 (Conv2D)               (None, None, None, 3 864         input_1[0][0]                    
__________________________________________________________________________________________________
batch_normalization_1 (BatchNor (None, None, None, 3 96          conv2d_1[0][0]                   
__________________________________________________________________________________________________
activation_1 (Activation)       (None, None, None, 3 0           batch_normalization_1[0][0]      

carlos-aguayo

carlos-aguayo

license: gpl-3.0

carlos-aguayo

The Project Gutenberg EBook of The Republic, by Plato

This eBook is for the use of anyone anywhere at no cost and with
almost no restrictions whatsoever.  You may copy it, give it away or
re-use it under the terms of the Project Gutenberg License included
with this eBook or online at www.gutenberg.org


Title: The Republic

carlos-aguayo

import pandas as pd
from xgboost import XGBClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import LabelEncoder

dataset = pd.read_csv('https://github.com/primaryobjects/voice-gender/raw/master/voice.csv', header=0).values
x = dataset[:, :-1]
y = dataset[:, -1]

carlos-aguayo

carlos-aguayo