conftrace_

von neumann winner

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

dueling bandit (2) regret bound (2) nash equilibrium (2) multi-criteria optimization (1) policy space (1) preference-based learning (1) sparse reward (1) blackwell approachability (1) contextual bandit (1) pairwise comparison (1)

Papers

Is RLHF More Difficult than Standard RL? A Theoretical Perspective NeurIPS 2023 Preference learning along multiple criteria: A game-theoretic perspective NeurIPS 2020 Instance-dependent Regret Bounds for Dueling Bandits COLT 2016 Contextual Dueling Bandits COLT 2015