Cherry-picking the best result

[yyrkoon27]

Dear TA,

Consider the following two cases:

1. Training up to an episode (e.g. 600) when the average reward of the past 100 episodes is already 200.0
2. Training up to the final episode (1000) when the average reward of the past 100 episodes might be 197.0

In general, which model should we use for testing?

Thank you very much!

[BIGBALLON]

hello, @yyrkoon27

In fact, 300 epochs is enough for converging.
So you can modify the max training epoch or change the epsilon.