google / google/dopamine

[Question] Value of tf.train.RMSPropOptimizer.momentum in dqn_nature.gin

Open
#43 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
10.9k
Forks
1.4k
PR merge metrics
No merged PRs in 30d

Description

First, thanks for sharing dopamine with all of us. It definitely improves productivity!

In the Minh et al. (2015) Nature paper on DQN, Extended Data Table 1 lists the gradient momentum as 0.95. However, in dqn_nature.gin the value seems to be set to 0.0:

tf.train.RMSPropOptimizer.learning_rate = 0.00025
tf.train.RMSPropOptimizer.decay = 0.95
tf.train.RMSPropOptimizer.momentum = 0.0
tf.train.RMSPropOptimizer.epsilon = 0.00001
tf.train.RMSPropOptimizer.centered = True

I believe this particular configuration file is supposed to offer the same hyperparameter settings as the Nature paper. Or perhaps I'm not interpreting the parameters correctly. Anyway, should it be 0.0 or 0.95?

Thanks much!

--Ted

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.