HAVER: Instance-Dependent Error Bounds for Maximum Mean Estimation and Applications to Q-Learning and Monte Carlo Tree Search

Documenti analoghi

• $\varepsilon$-Good Action Identification in Fixed-Budget Monte Carlo Tree Search
  di: Li, Yinan, et al.
  Pubblicazione: (2026)
• Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification
  di: Balagopalan, Kapilan, et al.
  Pubblicazione: (2024)
• Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood Estimation
  di: Zhao, Runze, et al.
  Pubblicazione: (2025)
• Nearly Optimal Active Preference Learning and Its Application to LLM Alignment
  di: Zhao, Yao, et al.
  Pubblicazione: (2026)
• Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits
  di: Jang, Kyoungseok, et al.
  Pubblicazione: (2024)