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

Tushar-N

import torch
import torch.nn as nn
from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence

seqs = ['gigantic_string','tiny_str','medium_str']

# make <pad> idx 0
vocab = ['<pad>'] + sorted(set(''.join(seqs)))

# make model

jeasinema

#!/usr/bin/env python
# -*- coding:UTF-8 -*-

import torch
import torch.nn as nn
import torch.nn.init as init


def weight_init(m):
    '''