Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives

Documenti analoghi

• Adversarial Multi-dueling Bandits
  di: Gajane, Pratik
  Pubblicazione: (2024)
• Utility-based Dueling Bandits as a Partial Monitoring Game
  di: Gajane, Pratik, et al.
  Pubblicazione: (2015)
• Fairness in two-player zero-sum games with bandit feedback
  di: Akash, S, et al.
  Pubblicazione: (2026)
• The Sampling Complexity of Condorcet Winner Identification in Dueling Bandits
  di: Saad, El Mehdi, et al.
  Pubblicazione: (2026)
• Best-of-Both-Worlds Algorithms for Linear Contextual Bandits
  di: Kuroki, Yuko, et al.
  Pubblicazione: (2023)