greedy-sampling

Tag

Cards List
#greedy-sampling

When Greedy Sampling Explores: KL-Regularized Contextual Bandits without Eluder-Dimension Dependence

arXiv cs.LG · yesterday Cached

This paper studies KL-regularized contextual bandits and shows that greedy sampling can achieve logarithmic regret without explicit eluder-dimension dependence for both reward and preference feedback.

0 favorites 0 likes
← Back to home

Submit Feedback