https://ki-seki.github.io/tags/multi-armed-bandit/ Recent content in Multi-Armed-Bandit on The Kiseki Log Hugo -- 0.146.0 en 2023-2026 Shichao Song CC BY-SA 4.0 Thu, 30 Apr 2026 17:13:15 +0800 https://ki-seki.github.io/posts/260430-multi-armed-bandit/ Thu, 30 Apr 2026 14:25:31 +0800 https://ki-seki.github.io/posts/260430-multi-armed-bandit/ The multi-armed bandit problem is a classic exploration–exploitation dilemma in reinforcement learning. Lilian Weng’s post is an excellent introduction, but some mathematical details and motivations can be cryptic. This article annotates it with step-by-step explanations and supplementary notes.