Limits RegistryPUBLIC RECORDLimits RegistryResearch Console →UCB1 has logarithmic instance-dependent expected regret for bounded iid arm rewards.
The question, scope, and sources behind this Registry record.
Under the recorded reinforcement learning model, establish expected regret = O(sum_i (ln T)/Delta_i).
Current frontiers derived from accepted Claims.
Assertions tied to evidence, attribution, and review.
The frontier as it changed over time.
Only accepted Claims matching the current specification contribute to the displayed bounds. Strict inequalities remain open; contradictory Claims require editorial review.
No accepted machine-checked reproductions are recorded for this Limit.
Limits Registry. LR-003637. UCB1 stochastic-bandit regret bound. 2026.