Runs YAPF on individual notebook cells using yapf_api.
To skip a cell formatting (for example with jupyter-custom syntax, add # noqa to the first line of the cell.
Remove newlines at end of cells.
Uses the style_format file .style.yapf.
Has a dry run option for checking proper formatting (f.e. in a Git hook).
| """ 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 |