English
Related papers

Related papers: Bayesian Preference Learning for Test-Time Steerab…

200 papers

Preference-based reinforcement learning (RL) offers a promising approach for aligning policies with human intent but is often constrained by the high cost of human feedback. In this work, we introduce PrefVLM, a framework that integrates…

Machine Learning · Computer Science 2025-02-04 Udita Ghosh , Dripta S. Raychaudhuri , Jiachen Li , Konstantinos Karydis , Amit Roy-Chowdhury

Multi-objective alignment aims to align LLM responses with multiple human preference objectives. Among existing methods, guiding the generation of frozen LLMs through autoregressive reward models (ARMs) to accomplish multi-objective…

Computation and Language · Computer Science 2026-02-11 Hongyan Xie , Yikun Ban , Ruiyu Fang , Zixuan Huang , Deqing Wang , Jianxin Li , Yitong Yao , Chao Wang , Shuangyong Song

The reward model has become increasingly important in alignment, assessment, and data construction for large language models (LLMs). Most existing researchers focus on enhancing reward models through data improvements, following the…

Computation and Language · Computer Science 2025-01-09 Shujun Liu , Xiaoyu Shen , Yuhang Lai , Siyuan Wang , Shengbin Yue , Zengfeng Huang , Xuanjing Huang , Zhongyu Wei

Process Reward Models (PRMs) have emerged as a promising approach to enhance the reasoning capabilities of large language models (LLMs) by guiding their step-by-step reasoning toward a final answer. However, existing PRMs either treat each…

Machine Learning · Computer Science 2026-03-02 Zheng Zhang , Ziwei Shan , Kaitao Song , Yexin Li , Kan Ren

The goal of inverse reinforcement learning (IRL) is to infer a reward function that explains the behavior of an agent performing a task. The assumption that most approaches make is that the demonstrated behavior is near-optimal. In many…

Machine Learning · Computer Science 2020-11-20 Luis Haug , Ivan Ovinnikov , Eugene Bykovets

Inverse reinforcement learning (IRL) infers a reward function from demonstrations, allowing for policy improvement and generalization. However, despite much recent interest in IRL, little work has been done to understand the minimum set of…

Machine Learning · Computer Science 2019-08-19 Daniel S. Brown , Scott Niekum

Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes…

Machine Learning · Computer Science 2019-06-25 Rohin Shah , Noah Gundotra , Pieter Abbeel , Anca D. Dragan

Reinforcement Learning from Verifiable Rewards (RLVR) suffers from exploration inefficiency, where models struggle to generate successful rollouts, resulting in minimal learning signal. This challenge is particularly severe for tasks that…

Machine Learning · Computer Science 2026-03-20 Saaket Agashe , Jayanth Srinivasa , Gaowen Liu , Ramana Kompella , Xin Eric Wang

Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. However, a notable limitation of PbRL is its dependency on substantial human feedback. This dependency stems…

Machine Learning · Computer Science 2024-05-30 Fengshuo Bai , Rui Zhao , Hongming Zhang , Sijia Cui , Ying Wen , Yaodong Yang , Bo Xu , Lei Han

Bayesian Reinforcement Learning (RL) is capable of not only incorporating domain knowledge, but also solving the exploration-exploitation dilemma in a natural way. As Bayesian RL is intractable except for special cases, previous work has…

Artificial Intelligence · Computer Science 2013-06-14 Kenji Kawaguchi , Mauricio Araya

Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs), but the performance is still underwhelming due to too much noisy preference data yielded in the loop. To combat…

Computation and Language · Computer Science 2024-09-18 Jianing Wang , Yang Zhou , Xiaocheng Zhang , Mengjiao Bao , Peng Yan

Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. The RLHF process typically starts by training a reward model (RM) using human preference…

Machine Learning · Computer Science 2024-06-19 Haoxiang Wang , Wei Xiong , Tengyang Xie , Han Zhao , Tong Zhang

Large language models (LLMs) can adapt to new tasks through in-context learning (ICL) based on a few examples presented in dialogue history without any model parameter update. Despite such convenience, the performance of ICL heavily depends…

Computation and Language · Computer Science 2024-06-18 Siyin Wang , Chao-Han Huck Yang , Ji Wu , Chao Zhang

Bayesian reinforcement learning (BRL) offers a decision-theoretic solution for reinforcement learning. While "model-based" BRL algorithms have focused either on maintaining a posterior distribution on models or value functions and combining…

Machine Learning · Computer Science 2020-07-03 Hannes Eriksson , Emilio Jorge , Christos Dimitrakakis , Debabrota Basu , Divya Grover

Invariant Causal Prediction (Peters et al., 2016) is a technique for out-of-distribution generalization which assumes that some aspects of the data distribution vary across the training set but that the underlying causal mechanisms remain…

Machine Learning · Computer Science 2021-03-30 Elan Rosenfeld , Pradeep Ravikumar , Andrej Risteski

Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewarding tasks, GRMs generate reasoning chains ending with…

Computation and Language · Computer Science 2026-05-04 Zongqi Wang , Rui Wang , Yuchuan Wu , Yiyao Yu , Pinyi Zhang , Shaoning Sun , Yujiu Yang , Yongbin Li

Multi-objective reinforcement learning (MORL) is a structured approach for optimizing tasks with multiple objectives. However, it often relies on pre-defined reward functions, which can be hard to design for balancing conflicting goals and…

Machine Learning · Computer Science 2025-07-21 Ni Mu , Yao Luan , Qing-Shan Jia

Reward models (RMs) are central to aligning large language models (LLMs) with human preferences, powering RLHF and advanced decoding strategies. While most prior work focuses on single-step generation, real-world applications increasingly…

Artificial Intelligence · Computer Science 2026-04-21 Xingyu Fan , Wei Shao , Jiacheng Liu , Linqi Song , Pheng Ann Heng

Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it remains unclear how to jointly learn reward functions from heterogeneous feedback types such as…

Machine Learning · Computer Science 2026-02-18 Raphaël Baur , Yannick Metz , Maria Gkoulta , Mennatallah El-Assady , Giorgia Ramponi , Thomas Kleine Buening

Large language models (LLMs) have been widely deployed across numerous fields. Reinforcement Learning from Human Feedback (RLHF) leverages reward models (RMs) as proxies for human preferences to align LLM behaviors with human values, making…

Machine Learning · Computer Science 2025-11-26 Shuyi Zhang , Wei Shi , Sihang Li , Jiayi Liao , Hengxing Cai , Xiang Wang