×
Instructions:
You have a total of 30 plays to maximize your reward.
At each play, select an arm to play and receive a reward of 0 or 1.
To help your decision, you have access to the following information:
- Rewards: The total reward from each arm.
- Plays: The total number of times you have played each arm.
- Estimated Probs: total reward/total plays, the estimated success probabilities of each arm.
- UCBs: The UCB of each arm (according to Auer et al. 2002).
