ConceptStochastic Contextual Bandit / 上下文Bandit
Stochastic Contextual Bandit
A stochastic contextual bandit is a class of sequential decision models in which the learner observes context at each step, selects an action, and receives the reward of only the chosen action. It faces the challenge of counterfactual inference and is widely applied in recommender systems, advertising, and clinical trials.
Timeline (last 90 days)
Oct 16
Stochastic contextual bandits do not involve state transitions, so they are easier to analyze theoretically than full reinforcement learning, and their policy evaluation faces the challenges of counterfactual inference and distribution shift correction.
Unverified50%