| #!/usr/bin/env python | |
| # -*- coding:UTF-8 -*- | |
| import torch | |
| import torch.nn as nn | |
| import torch.nn.init as init | |
| def weight_init(m): | |
| ''' |
| 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 |
| """ | |
| A bare bones examples of optimizing a black-box function (f) using | |
| Natural Evolution Strategies (NES), where the parameter distribution is a | |
| gaussian of fixed standard deviation. | |
| """ | |
| import numpy as np | |
| np.random.seed(0) | |
| # the function we want to optimize |
| """ 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 |
| sudo curl -o /usr/local/bin/imgcat -O https://raw.githubusercontent.com/gnachman/iTerm2/master/tests/imgcat && sudo chmod +x /usr/local/bin/imgcat | |
| # If you have a better way to fix the permissions, comment below! |
People
 :bowtie: |
😄 :smile: |
😆 :laughing: |
|---|---|---|
😊 :blush: |
😃 :smiley: |
:relaxed: |
😏 :smirk: |
😍 :heart_eyes: |
😘 :kissing_heart: |
😚 :kissing_closed_eyes: |
😳 :flushed: |
😌 :relieved: |
😆 :satisfied: |
😁 :grin: |
😉 :wink: |
😜 :stuck_out_tongue_winking_eye: |
😝 :stuck_out_tongue_closed_eyes: |
😀 :grinning: |
😗 :kissing: |
😙 :kissing_smiling_eyes: |
😛 :stuck_out_tongue: |
