| from __future__ import print_function | |
| import imageio | |
| from PIL import Image | |
| import numpy as np | |
| import keras | |
| from keras.layers import Input, Dense, Conv2D, MaxPooling2D, AveragePooling2D, ZeroPadding2D, Dropout, Flatten, Concatenate, Reshape, Activation | |
| from keras.models import Model | |
| from keras.regularizers import l2 | |
| from keras.optimizers import SGD |
| """ 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 |
By @foldleft.bsky.social, see also Unfollow everyone on bsky.app.
https://twitter.com/YOUR_USER_NAME/following// Unfollow everyone on twitter.com, by Jamie Mason (https://twitter.com/fold_left)