Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback
read the original abstract
We investigate the feasibility of learning from a mix of both fully-labeled supervised data and contextual bandit data. We specifically consider settings in which the underlying learning signal may be different between these two data sources. Theoretically, we state and prove no-regret algorithms for learning that is robust to misaligned cost distributions between the two sources. Empirically, we evaluate some of these algorithms on a large selection of datasets, showing that our approach is both feasible and helpful in practice.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewards
The MLA-UCB algorithm uses ML-generated surrogate rewards from auxiliary data to provably lower cumulative regret in multi-armed bandits, achieving asymptotic optimality under joint Gaussian assumptions without requir...
-
Identifiable Latent Bandits: Leveraging observational data for personalized decision-making
Identifiable latent bandits apply nonlinear ICA to observational data to recover representations sufficient for inferring optimal actions in new instances, shortening exploration time.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.