conftrace_

aggregate bandit feedback

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

distorted linear bandit (1) online mdp (1) hedging scheme (1) near-optimal regret (1) q-functions ensemble (1) adversarially changing loss (1) randomization technique (1) finite horizon (1) self-concordant barrier (1) linear mdp (1)

Papers

Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback ICML 2025 Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback ICML 2024 Online Markov Decision Processes with Aggregate Bandit Feedback COLT 2021