On the Computational Tractability of Robust Bandits
Researchers give a polynomial-time robust bandit learner with near-square-root regret and show nearby variants are NP-hard.
Stories per day · 30 days
1 stories, newest first · one card per story
1 stories, newest first · one card per story
Researchers give a polynomial-time robust bandit learner with near-square-root regret and show nearby variants are NP-hard.
Today 367 readers · 405 views · 34 reads · all time 109K views