English
Related papers

Related papers: Preference-based Reinforcement Learning beyond Pai…

200 papers

Preference alignment is pivotal for empowering large language models (LLMs) to generate helpful and harmless responses. However, the performance of preference alignment is highly sensitive to the prevalent noise in the preference data.…

Machine Learning · Computer Science 2024-05-29 Xize Liang , Chao Chen , Shuang Qiu , Jie Wang , Yue Wu , Zhihang Fu , Zhihao Shi , Feng Wu , Jieping Ye

Group Relative Policy Optimization(GRPO) has become a cornerstone of modern reinforcement learning alignment, prized for its efficacy in foregoing an explicit value-critic by leveraging reward normalization across sampled trajectory…

Computation and Language · Computer Science 2026-05-29 Redacted by arXiv

Preference-based reinforcement learning (RL) is a key paradigm for aligning policies with human judgments, yet its theoretical behavior in distributed settings where preference data are fragmented across heterogeneous users remains poorly…

Machine Learning · Computer Science 2026-05-21 Zhanhong Jiang

Preference-based reinforcement learning (PBRL) in the offline setting has succeeded greatly in industrial applications such as chatbots. A two-step learning framework where one applies a reinforcement learning step after a reward modeling…

Preference-based reinforcement learning (PBRL) offers a promising alternative to explicit reward engineering by learning from pairwise trajectory comparisons. However, real-world preference data often comes from heterogeneous annotators…

Aligning Large Language Model (LLM) responses with human preferences is vital for building safe and controllable AI systems. While preference optimization methods based on Plackett-Luce (PL) and Bradley-Terry (BT) models have shown promise,…

Artificial Intelligence · Computer Science 2026-03-23 Xiandong Zou , Wanyu Lin , Yuchen Li , Pan Zhou

Reinforcement learning is the method of choice to train models in sampling-based setups with binary outcome feedback, such as navigation, code generation, and mathematical problem solving. In such settings, models implicitly induce a…

Reinforcement learning (RL) is pivotal for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, existing dLLM policy optimization methods suffer from two critical reliability bottlenecks: (1) reward…

Computation and Language · Computer Science 2026-05-14 Leyi Pan , Shuchang Tao , Yunpeng Zhai , Zheyu Fu , Liancheng Fang , Minghua He , Lingzhe Zhang , Zhaoyang Liu , Bolin Ding , Aiwei Liu , Lijie Wen

Reinforcement learning (RL) algorithms aim to learn optimal decisions in unknown environments through experience of taking actions and observing the rewards gained. In some cases, the environment is not influenced by the actions of the RL…

Preference based alignment objectives implicitly assume that all human preferences are expressed with equal strength. In practice, however, preference strength varies across individuals and contexts -- a phenomenon established in behavioral…

Machine Learning · Computer Science 2026-01-13 Saki Imai , Pedram Heydari , Anthony Sicilia , Asteria Kaeberlein , Katherine Atwell , Malihe Alikhani

Direct Preference Optimization (DPO) has emerged as a de-facto approach for aligning language models with human preferences. Recent work has shown DPO's effectiveness relies on training data quality. In particular, clear quality differences…

Machine Learning · Computer Science 2025-01-28 Nirav Diwan , Tolga Ergen , Dongsub Shim , Honglak Lee

The use of Potential-Based Reward Shaping (PBRS) has shown great promise in the ongoing research effort to tackle sample inefficiency in Reinforcement Learning (RL). However, choosing the right potential function remains an open challenge.…

Machine Learning · Computer Science 2025-08-12 Giuseppe Canonaco , Leo Ardon , Alberto Pozanco , Daniel Borrajo

Instruction-fine-tuned large language models (LLMs) under 14B parameters continue to underperform on natural language understanding (NLU) tasks, often trailing smaller models like BERT-base on benchmarks such as GLUE and SuperGLUE.…

Computation and Language · Computer Science 2025-09-29 Bokai Hu , Sai Ashish Somayajula , Xin Pan , Pengtao Xie

This paper studies offline policy learning, which aims at utilizing observations collected a priori (from either fixed or adaptively evolving behavior policies) to learn an optimal individualized decision rule that achieves the best overall…

Machine Learning · Computer Science 2025-06-06 Ying Jin , Zhimei Ren , Zhuoran Yang , Zhaoran Wang

The theory of reinforcement learning has focused on two fundamental problems: achieving low regret, and identifying $\epsilon$-optimal policies. While a simple reduction allows one to apply a low-regret algorithm to obtain an…

Machine Learning · Computer Science 2022-06-23 Andrew Wagenmaker , Max Simchowitz , Kevin Jamieson

In the Bayesian Reinforcement Learning (BRL) setting, agents try to maximise the collected rewards while interacting with their environment while using some prior knowledge that is accessed beforehand. Many BRL algorithms have already been…

Artificial Intelligence · Computer Science 2016-09-28 Michael Castronovo , Damien Ernst , Adrien Couetoux , Raphael Fonteneau

Most research in Bayesian optimization (BO) has focused on \emph{direct feedback} scenarios, where one has access to exact values of some expensive-to-evaluate objective. This direction has been mainly driven by the use of BO in machine…

Machine Learning · Computer Science 2021-09-02 Eero Siivola , Akash Kumar Dhaka , Michael Riis Andersen , Javier Gonzalez , Pablo Garcia Moreno , Aki Vehtari

Offline reinforcement learning has become one of the most practical RL settings. However, most existing works on offline RL focus on the standard setting with scalar reward feedback. It remains unknown how to universally transfer the…

Machine Learning · Computer Science 2024-10-25 Yinglun Xu , David Zhu , Rohan Gumaste , Gagandeep Singh

Aligning Large Language Models (LLMs) with human preferences is crucial, but standard methods like Reinforcement Learning from Human Feedback (RLHF) are often complex and unstable. In this work, we propose a new, simpler approach that…

Machine Learning · Computer Science 2026-01-27 Saeed Najafi , Alona Fyshe

Preference-based feedback is important for many applications in machine learning where evaluation of a reward function is not feasible. Notable recent examples arise in preference alignment for large language models, including in…