Pinned Loading

1. AASMA AASMA Public

   Autonomous agents simulation

   JavaScript

2. BD BD Public

   Bases de Dados IST

   PHP

3. DAD DAD Public

   DAD IST 2017

   C#

4. loglytics_library loglytics_library Public

   Java

5. SAD-2 SAD-2 Public

   Decision Support Systems 2017 Class Project

   R

6. Training a Neural Network ATARI Pong... Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels

   1

   """ Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """

   2

   import numpy as np

   3

   import cPickle as pickle

   4

   import gym

   5