I have a problem that can be optimized by taking five actions, and finally, after a series of steps to achieve a solution.

The actions (1 to 5) are picked randomly. A time-step (epoch) is concluded every time five actions are taken. The outcome is influenced by the sequence of actions and the time-step.

E.g Action sequence: 5,4,2,1,3 may be better for time 3 than time 9.

Time 1 Action   A1  A5  A3  A4  A2
Time 1 Outcome  0   0   5   122 6

Time 2 Action   A5  A3  A2  A1  A4
Time 2 Outcome  42  0   9   80  7

Time 3 Action   A3  A2  A1  A4  A5
Time 3 Outcome  13  43  1   0   10


Time N Action   A2  A3  A4  A5  A4
Time N Outcome  15  100 120 42  75

The goal is to collect as many points as possible by the Nth round.

Should I approach this problem with RNN, or is there a more suitable theory/algorithm?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.