| # Authors: Mathieu Blondel, Vlad Niculae | |
| # License: BSD 3 clause | |
| import numpy as np | |
| def _gen_pairs(gen, max_iter, max_inner, random_state, verbose): | |
| rng = np.random.RandomState(random_state) | |
| # if tuple, interpret as randn |
This is how I managed to build TensorFlow 2.0 on Ubuntu 18.04 (x86_64) with Bazelisk:
$ sudo apt update
$ sudo apt full-upgrade
$ sudo apt install curl
# Install Bazelisk.
$ sudo curl -Lo /usr/local/bin/bazel https://github.com/bazelbuild/bazelisk/releases/download/v1.1.0/bazelisk-linux-amd64
$ sudo chmod +x /usr/local/bin/bazel
| """ 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 |