collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

An Information-Theoretic Definition for Open-Ended Learning

Wanqiao Xu, Yifan Zhu, Benjamin Van Roy

A growing body of work points to the great promise of AI systems that can continually expand their capabilities as they operate in an open-ended environment. But yet there is no co…

cs.LG2026

Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems

Jonathan Colaço Carr, Jonathan Colaço Carr, Prakash Panangaden +2

Reinforcement learning with scalar rewards is widely used for aligning machine-learning systems with user preferences. But, pairwise preferences are often more natural for users to…

cs.LG2026

Efficient Exploration at Scale

Seyed Mohammad Asghari, Chris Chute, Vikranth Dwaracherla +5

We develop an online learning algorithm that dramatically improves the data efficiency of reinforcement learning from human feedback (RLHF). Our algorithm incrementally updates rew…

cs.LG2025

Capacity-Constrained Continual Learning

Zheng Wen, Doina Precup, Benjamin Van Roy +1

Any agents we can possibly build are subject to capacity constraints, as memory and compute resources are inherently finite. However, comparatively little attention has been dedica…

cs.LG2024

Satisficing Exploration for Deep Reinforcement Learning

Dilip Arumugam, Saurabh Kumar, Ramki Gummadi +1

A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environme…

cs.LG2024

Exploration Unbound

Dilip Arumugam, Wanqiao Xu, Benjamin Van Roy

A sequential decision-making agent balances between exploring to gain new knowledge about an environment and exploiting current knowledge to maximize immediate reward. For environm…