conftrace_

best-policy identification

7 papers

Explore in graph

Also known as

BPI

Co-occurring keywords · papers mentioning both

sample complexity (5) reward-free exploration (3) markov decision process (3) risk-sensitive reinforcement learning (2) generative model (2) discounted markov decision process (1) pac reinforcement learning (1) active coverage (1) optimal sample allocation (1) minimax guarantee (1)

Papers

Tight Sample Complexity Bounds for Entropic Best Policy Identification COLT 2026 Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity ICLR 2024 Active Coverage for PAC Reinforcement Learning COLT 2023 Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path ICLR 2023 Adaptive Reward-Free Exploration ALT 2021 Adaptive Sampling for Best Policy Identification in Markov Decision Processes ICML 2021 Fast active learning for pure exploration in reinforcement learning ICML 2021