Design of Experiments for Stochastic Contextual Linear Bandits
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:ZM52GTA7record.jsonopen to challenge →
read the original abstract
In the stochastic linear contextual bandit setting there exist several minimax procedures for exploration with policies that are reactive to the data being acquired. In practice, there can be a significant engineering overhead to deploy these algorithms, especially when the dataset is collected in a distributed fashion or when a human in the loop is needed to implement a different policy. Exploring with a single non-reactive policy is beneficial in such cases. Assuming some batch contexts are available, we design a single stochastic policy to collect a good dataset from which a near-optimal policy can be extracted. We present a theoretical analysis as well as numerical experiments on both synthetic and real-world datasets.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
Logging Policy Design for Off-Policy Evaluation
Derives optimal logging policies for off-policy evaluation by balancing reward concentration against action coverage in known, unknown, and partially known regimes of target policy and rewards.
-
Anytime-valid Optimal Policy Identification
Constructs a time-indexed set S_t retaining the true optimal policy uniformly over time with high probability, enabling early stopping with sample complexity O((log |Π| + log log(1/Δ_min))/Δ_min²) when the optimum is unique.
-
Logging Policy Design for Off-Policy Evaluation
Derives optimal logging policies for minimizing off-policy evaluation error under known, unknown, and partially known target policies and reward distributions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.