conftrace_

logged bandit feedback

3 papers

Explore in graph

Also known as

LBF

Co-occurring keywords · papers mentioning both

counterfactual risk minimization (2) contextual bandit (2) surrogate policy (1) propensity scoring (1) inverse propensity scoring (1) empirical risk (1) structural risk minimization (1) deep learning (1) policy learning (1) object recognition (1)

Papers

Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy ICLR 2019 Deep Learning with Logged Bandit Feedback ICLR 2018 Batch Learning from Logged Bandit Feedback through Counterfactual Risk Minimization JMLR 2015