paper-with-me

홈 › Papers

Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems

2026-05-29 · Jonathan Colaço Carr, Prakash Panangaden, Doina Precup, Benjamin Van Roy arxiv

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 specify than scalar rewards, and they express certain goals that scalar rewards cannot. Methods for reinforcement learning with pairwise preferences have thus received growing interest. Unfortunately, these methods are inefficient in problems with long time horizons, and they lack guarantees on the performance of Markov policies relative to history-dependent policies, which bridge the theory and practice of reinforcement learning. We address these limitations in a new problem setting for reinforcement learning with pairwise preferences called the \textit{Markov decision contest}. In this setting, we prove that stationary Markov policies perform just as well as history-dependent policies; that the problem of recovering an optimal policy exactly is in P; and that a simple iterative algorithm converges to an optimal policy at a sublinear rate. Lastly, we implement a deep-learning variant of our iterative algorithm and demonstrate its efficiency in long-term decision problems that require function approximation.

📄 PDF Abstract BibTeX arXiv:2606.00367

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment

2024-03-25 · Feiteng Fang, Liang Zhu, Min Yang, Xi Feng 외

Reinforcement learning from human feedback (RLHF) is a crucial technique in aligning large language models (LLMs) with human preferences, ensuring these LLMs behave in beneficial and comprehensible ways to users. However…

Contrastive Learningreinforcement-learningReinforcement Learning

Characterization of an inconsistency ranking for pairwise comparison matrices

2016-10-24 · László Csató

Pairwise comparisons between alternatives are a well-known method for measuring preferences of a decision-maker. Since these often do not exhibit consistency, a number of inconsistency indices has been introduced in orde…

A density estimation perspective on learning from pairwise human preferences

2023-11-23 · Vincent Dumoulin, Daniel D. Johnson, Pablo Samuel Castro, Hugo Larochelle 외

Learning from human feedback (LHF) -- and in particular learning from pairwise preferences -- has recently become a crucial ingredient in training large language models (LLMs), and has been the subject of much research. …

Density Estimation

Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback

2023-05-26 · Tom Bewley, Jonathan Lawry, Arthur Richards

We propose a method to capture the handling abilities of fast jet pilots in a software model via reinforcement learning (RL) from human preference feedback. We use pairwise preferences over simulated flight trajectories …

Reinforcement Learning (RL)

A General Theoretical Paradigm to Understand Learning from Human Preferences

2023-10-18 · Mohammad Gheshlaghi Azar, Mark Rowland, Bilal Piot, Daniel Guo 외

The prevalent deployment of learning from human preferences through reinforcement learning (RLHF) relies on two important approximations: the first assumes that pairwise preferences can be substituted with pointwise rewa…