Exploiting the Natural Exploration In Contextual Bandits

30 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The Frontiers of Fairness in Machine Learning (2018, background): “For example, [BBK17] and [KMR + 18] give conditions under which linear learners need not explore at all in bandit settings, thereby allowing for best-eﬀort service to each arriving individual, obviating the tension between ethical treatment of individuals and learning.”
Offline Reinforcement Learning from Human Feedback in Real-World Sequence-to-Sequence Tasks (2020, background): “This has been observed for the case of online advertising (Chapelle and Li, 2011) and investigated theoretically (Bastani et al., 2017).”
Human Interaction with Recommendation Systems (2017, background): “Recent work by Bastani et al. [2017], Qiang and Bayati [2016] consider natural exploration in contextual bandit problems, and show that a modified greedy algorithm performs well.”
Practical Evaluation and Optimization of Contextual Bandit Algorithms (2018, methodology): “A possible reason for this success is the diversity that is inherently present in the distribution of contexts across actions, which has been shown to yield no-regret guarantees under various assumptions (Bastani et al., 2017; Kannan et al., 2018).”
Counterfactual Learning for Machine Translation: Degeneracies and Solutions (2017, background): “This phenomenon has recently been given a formal account by Bastani et al. (2017) and has not been analyzed formally in this paper.”