1.4k citations · 4.5k across the 58 of their papers we have counts for
27 papers · 1 filter
Steering Safely or Off a Cliff? Rethinking Specificity and Robustness in Inference-Time Interventions
Navita Goyal, Hal Daumé
Model steering, which involves intervening on hidden representations at inference time, has emerged as a lightweight alternative to finetuning for precisely controlling large langu…
Reinforcement Learning with Convex Constraints
Sobhan Miryoosefi, Kianté Brantley, Hal Daumé +2
In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as cons…
Meta-Learning for Contextual Bandit Exploration
Amr Sharaf, Hal Daumé
We describe MELEE, a meta-learning algorithm for learning a good exploration policy in the interactive contextual bandit setting. Here, an algorithm must take actions based on cont…
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback
Chicheng Zhang, Alekh Agarwal, Hal Daumé +2
We investigate the feasibility of learning from a mix of both fully-labeled supervised data and contextual bandit data. We specifically consider settings in which the underlying le…
Contextual Memory Trees
Wen Sun, Alina Beygelzimer, Hal Daumé +2
We design and study a Contextual Memory Tree (CMT), a learning memory controller that inserts new memories into an experience store of unbounded size. It is designed to efficiently…
Hierarchical Imitation and Reinforcement Learning
Hoang M. Le, Nan Jiang, Alekh Agarwal +3
We study how to effectively leverage expert feedback to learn sequential decision-making policies. We focus on problems with sparse rewards and long time horizons, which typically…