Second Brain
Search
Search
Dark mode
Light mode
Explorer
Tag: topic/multi-armed-bandits
8 items with this tag.
Sep 23, 2026
Q: Multi-armed and contextual bandits, Bayesian optimisation, sequential Bayesian experimental design / deep adaptive design, dynamic treatment regimes with Q- and A-learning, switchback experiments and RLHF all choose actions from accumulating data. Laid out on one map, what is each optimizing, what is the state, and what feedback does it assume?
type/qa
topic/multi-armed-bandits
topic/bayesian-experimental-design
topic/causal-inference
topic/online-experimentation
topic/large-language-models
topic/machine-learning
Sep 23, 2026
Q: Does peeking (optional stopping) matter for a Bayesian? Reconcile the frequentist peeking problem, always-valid p-values / mSPRT and confidence sequences with the likelihood principle, Thompson sampling and sequential Bayesian experimental design.
type/qa
topic/bayesian-statistics
topic/online-experimentation
topic/research-methodology
topic/multi-armed-bandits
topic/calibration
Sep 18, 2026
Approximate Thompson Sampling and Practical Extensions
source/ingested
topic/bayesian-experimental-design
topic/multi-armed-bandits
type/concept
type/example
doc/paper
Sep 18, 2026
Bernoulli Bandit and Thompson Sampling Algorithm
source/ingested
topic/bayesian-experimental-design
topic/multi-armed-bandits
type/definition
type/concept
doc/paper
Sep 18, 2026
Contextual and Linear Bandits
source/ingested
topic/bayesian-experimental-design
topic/multi-armed-bandits
type/concept
type/example
doc/paper
Sep 18, 2026
Multi-Armed Bandits and Thompson Sampling - Overview
source/ingested
topic/bayesian-experimental-design
topic/multi-armed-bandits
type/overview
doc/paper
Sep 18, 2026
Regret Bounds for Thompson Sampling
source/ingested
topic/bayesian-experimental-design
topic/multi-armed-bandits
type/theorem
type/concept
doc/paper
Sep 18, 2026
UCB and Greedy Algorithms for Bandits
source/ingested
topic/bayesian-experimental-design
topic/multi-armed-bandits
type/concept
type/definition
doc/paper