Thanks for your excellent contributions, it is really helpful!
I am not sure if it is an issue, but it confused me at the beginning. Here is the thing. #1_getting_started.ipynb
Even though they are evaluated by the same agent, the difference between mean_reward_before_train and mean_reward is large. I checked the code and realized that mean_reward uses deterministic action while mean_reward_before_train does not.
If this is not intentionally set up to encourage people to investigate the implementation. Probably it would be better to make them consistent.
Hello,
Thanks for your excellent contributions, it is really helpful!
I am not sure if it is an issue, but it confused me at the beginning. Here is the thing. #1_getting_started.ipynb
Even though they are evaluated by the same agent, the difference between
mean_reward_before_train
andmean_reward
is large. I checked the code and realized thatmean_reward
uses deterministic action whilemean_reward_before_train
does not.If this is not intentionally set up to encourage people to investigate the implementation. Probably it would be better to make them consistent.
Best, J