The minimalisitic exploration and exploitation task

The entire experiment will consist of 180 rounds(For demonstration purpose, here we only set 6 trials for each context).
In each task, you will act as a tourist exploring a foreign city, with the number of days varying from 5 to 10.
On the first day, you will randomly visit a restaurant to dine, and we will inform you of the restaurant's rating.
Afterwards, you can choose either “Go to a random new restaurant” or “Go back to the best restaurant so far”.
Ensure that after each selection you click the ✓ (confirm) button under both options.
Then we will inform you of the restaurant's rating.
We will accumulate the ratings of all the restaurants you chose during that round, and this sum will be your total score for that round.