{"paper":{"title":"Bandits with Side Observations: Bounded vs. Logarithmic Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Evrard Garcelon, R\\'emy Degenne, Vianney Perchet","submitted_at":"2018-07-10T10:15:30Z","abstract_excerpt":"We consider the classical stochastic multi-armed bandit but where, from time to time and roughly with frequency $\\epsilon$, an extra observation is gathered by the agent for free. We prove that, no matter how small $\\epsilon$ is the agent can ensure a regret uniformly bounded in time.\n  More precisely, we construct an algorithm with a regret smaller than $\\sum_i \\frac{\\log(1/\\epsilon)}{\\Delta_i}$, up to multiplicative constant and loglog terms. We also prove a matching lower-bound, stating that no reasonable algorithm can outperform this quantity."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03558","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}