conftrace_

optimization horizon

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

dynamic preference (1) alignment technique (1) influenceable reward (1) autoregressive process (1) multi-armed bandit (1) mdp (1) online learning algorithm (1) reward function (1) regret minimization (1) sequential decision making (1)

Papers

AI Alignment with Changing and Influenceable Reward Functions ICML 2024 Autoregressive Bandits AISTATS 2024