← all papers · overview

Exploration by Optimisation in Partial Monitoring

Abstract

We provide a simple and efficient algorithm for adversarial k-action d-outcome non-degenerate locally observable partial monitoring game for which the n-round minimax regret is bounded by 6(d+1) k^3/2 √n log(k), matching the best known information-theoretic upper bound. The same algorithm also achieves near-optimal regret for full information, bandit and globally observable games.

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).