Playing Rock, Paper, Scissors with LSTMs

Remembering sequences of data have huge applications in many areas, not the least of which includes gaming. Of course, producing a simple, clean example is another matter. Fortunately, examples abound on the internet and Chapter_2_5.py shows an example of using an LSTM to play Rock, Paper, Scissors.

Open up that sample file and follow these steps:

This example was pulled from https://github.com/hjpulkki/RPS, but the code needed to be tweaked in several places to get it to work for us.

1. Let's start as we normally do with the imports. For this sample, be sure to have Keras installed as we did for the last set of exercises:

import numpy as np
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense, LSTM

2. Then, we set some constants as shown:

EPOCH_NP = 100
INPUT_SHAPE = (1, -1, 1)
OUTPUT_SHAPE...