Claims near-minimax optimal regret for conversational contextual bandits via smoothed key-term exploration and adaptive conversation timing, but the proofs have serious gaps.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Leveraging the Power of Conversations: Optimal Key Term Selection in Conversational Contextual Bandits
Claims near-minimax optimal regret for conversational contextual bandits via smoothed key-term exploration and adaptive conversation timing, but the proofs have serious gaps.