conftrace_

complete policy regret

2 papers

Explore in graph

Also known as

CPR

Co-occurring keywords · papers mentioning both

regret bound (2) multi-armed bandit (2) tallying bandit (1) memory bounded adversary (1) repeated exposure optimality (1) successive elimination (1) policy regret (1) adaptive adversary (1) human memory (1) regret minimization (1)

Papers

Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality ICML 2023 Complete Policy Regret Bounds for Tallying Bandits COLT 2022