should model.py line 52 be tf.nn.relu instead of tf.nn.elu?

openai / universe-starter-agent

A starter agent that can solve a number of universe environments.

MIT License

1.1k stars 318 forks source link

should model.py line 52 be tf.nn.relu instead of tf.nn.elu? #97

Closed goodnamegood closed 6 years ago

goodnamegood commented 7 years ago

As titled. I think this line should be x = tf.nn.relu(conv2d(x, 32, "l{}".format(i + 1), [3, 3], [2, 2])) instead of x = tf.nn.elu(conv2d(x, 32, "l{}".format(i + 1), [3, 3], [2, 2]))

tlbtlbtlb commented 7 years ago

For the games we tested on, elu got slightly higher scores than relu. But universe-starter-agent is intended as a starting point, a framework for experimentation, so you should experiment with that and other modifications to see what gets the best results.