billh0420
billh0420
It seems to be necessary to increase the buffer_size for AverageReturnMetric to get better precision. One would think that increasing buffer_size would only speed up the computation (at a cost...
Currently, DQNAgent updates the target network periodically. Would it make sense to provide a target_update method in DQNAgent to update the target network? Reasons: 1. I find it confusing to...
There are several places where deprecated methods are being used. For example: "final Double d = new Double(value);" The suggested correction is: "final Double d = Double.valueOf(value);" I am willing...