pith. sign in

http://proceedings.mlr.press/v65/seldin17a/seldin17a.pdf An improved parametrization and analysis of the EXP3++ algorithm for stochastic and adversarial bandits

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

stat.ML 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Best of both worlds: Stochastic & adversarial best-arm identification

stat.ML · 2026-04-16 · unverdicted · novelty 7.0

No algorithm can be optimal in both stochastic and adversarial best-arm identification; a new parameter-free algorithm matches the derived lower bound up to log factors in stochastic cases while handling adversarial rewards.

citing papers explorer

Showing 1 of 1 citing paper.

  • Best of both worlds: Stochastic & adversarial best-arm identification stat.ML · 2026-04-16 · unverdicted · none · ref 27

    No algorithm can be optimal in both stochastic and adversarial best-arm identification; a new parameter-free algorithm matches the derived lower bound up to log factors in stochastic cases while handling adversarial rewards.