AI Paper Atlas

Research map / Bandits and online learning / Multi-armed bandits

Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk

Tianrui Chen, Aditya Gangrade, Venkatesh Saligrama

ICML 2022 · Bandits and online learning › Multi-armed bandits · approach: Optimal stochastic bandit algorithms · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use single-arm doubly optimistic index schema instead of policy-level (simplex) methodssafe bandit with single optimal arm · 4-arm Bernoulli instance, alpha=0.5, single optimal arm 3 (mu3=0.6)unsafe arm plays: about 550 vs at least 8000Improved
Use policy-level (BwCR, Pess) methods rather than per-arm index schemasafe bandit with multiple optimal policies · 4-arm instance, alpha=0.5expected unsafe plays E[U_t]Hurt
Replace Thompson sampling selection with KL-UCB-based index in the permissible-set scheme (TS with optimistic safety indices vs KL-UCB)drug trial data alpha=0.21 · Drug trial (Phase 2 RA data), alpha=0.21regret and unsafe playsHurt
Use BayesUCB safety index with Thompson sampling (TS+BayesUCB) instead of KL-UCB confidence boundssafe bandit on drug trial data · Drug trial (Phase 2 RA data), alpha=0.21regret and unsafe playsImproved
Naive Thompson sampling on safety posterior compared against fixed alpha (sigma sampled from Beta, Pi = {sigma<=alpha})safe bandit with nu*=alpha · simulation with nu*=alphaexpected regret: linear expected regretHurt
Uniform quantile schedule delta=1/(t+1) instead of conservative delta_t^k=(sqrt(8N) t log^3 t)^-1 in TS+BayesUCBTS+BayesUCB · simulationsregretImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy