They calculate their discount factor based on five years.

The discount factor determines the importance of future rewards.

If the discount factor meets or exceeds 1, the action values may diverge.

If the discount factor is high enough this price will be close to zero.

It is easy to verify that these are the correct discount factors.

Second, the following approximation to the discount factor is used:.

Thus the discount factor is replaced by since one must take into account the time value of money.

This is why the discount factor is used in the denominator.

In fact as discount factors tend to unity so does the temporary reputation become permanent.

If you are unfamiliar with this method, an industry expert will be able to advise on how to choose and apply discount factors.