Hello,
I would like to verify that there is indeed a typo in the statement of Question 1:
> Plot average reward for every 250 games during training, i.e. after the 50th game, plot the average reward of the first 250 games, after the 100th game, plot the average reward of games 51 to 100, etc.
The second part should probably say "...after the 250th game, plot the average reward of the first 250 games, after the 500th game, plot the average reward of games 251 to 500, etc."
I am assuming that 250 is the intended window since all subsequent questions also refer to this number, and also because with only 50 samples it is still very noisy. Am I right?
Thanks in advance! Best wishes,
Marie
