conftrace_

policy coverage

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

gap-dependent bound (1) suboptimality (1) online rlhf (1) win-rate-based selection (1) density ratio (1) theoretical bound (1) minimax optimal (1) kl regularization (1) sample complexity (1) transfer learning (1)

Papers

Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective ICML 2025 On Gap-dependent Bounds for Offline Reinforcement Learning NeurIPS 2022