Skip to main content
1 vote

UCB, Thompson sampling etc seems myopic/greedy for bandits?

The (binary) multi-armed bandit actually is a MDP with one state and $K$ actions. So your suggestion boils down to meta-learning: Find the parameters of one MDP that can solve another. Let's go with ...
maxy's user avatar
  • 233

Only top scored, non community-wiki answers of a minimum length are eligible