Is there a variant of Thompson Sampling that works with variable bandits?

Asked Mar 10 '22 at 23:16

Active Mar 12 '22 at 09:10

Viewed 52 times

Does there exist a variant of TS, such that, while computing the returns of multi-armed bandits, we have the possibility of introducing an extra bandit?

For instance, while we are applying TS to 3 slot machines, we come to know about the existence of a fourth slot machine. Therefore, we'd like to take that machine into account within our algorithm.

edited Mar 12 '22 at 09:10

nbro

39,006
12
98
176

asked Mar 10 '22 at 23:16

desert_ranger

1

So, are you asking about applying TS to bandit problems with a variable/dynamic number of actions? – nbro Mar 12 '22 at 09:10
Yes, that’s what I am asking. – desert_ranger Mar 12 '22 at 16:08

Is there a variant of Thompson Sampling that works with variable bandits?

0 Answers0