You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
If we have 2 actions and $\varepsilon=0.5$, the probability of selecting the greedy action is $0.5 + 0.25=0.75$. We add $0.25$ because we may select a random action with $\varepsilon=0.5$ which can be the greedy action itself. Since there are 2 actions, the "random" probability will be distributed equally $\frac{0.5}{2}=0.25$.
The text was updated successfully, but these errors were encountered:
Correct me if my following reasoning is wrong, but I would like to elaborate on your answer.
With probability 0.5 you select a greedy action and with probability 0.5 you select an action at random from the set {greed, non-greedy}. Thus the probability of selecting a greedy action becomes:
0.5 (from selecting greedy action) + 0.5*0.5 (probability of choosing from the set * probability to choose a greedy action from the set) = 0.75
We add the two probabilities because the two events are exclusive.
If we have 2 actions and$\varepsilon=0.5$ , the probability of selecting the greedy action is $0.5 + 0.25=0.75$ . We add $0.25$ because we may select a random action with $\varepsilon=0.5$ which can be the greedy action itself. Since there are 2 actions, the "random" probability will be distributed equally $\frac{0.5}{2}=0.25$ .
The text was updated successfully, but these errors were encountered: