English
Related papers

Related papers: Learning Pareto-Optimal Rewards from Noisy Prefere…

200 papers

Large foundation models pretrained on raw web-scale data are not readily deployable without additional step of extensive alignment to human preferences. Such alignment is typically done by collecting large amounts of pairwise comparisons…

Machine Learning · Computer Science 2024-06-13 Daiwei Chen , Yi Chen , Aniket Rege , Ramya Korlakai Vinayak

Multi-objective reinforcement learning (MORL) excels at handling rapidly changing preferences in tasks that involve multiple criteria, even for unseen preferences. However, previous dominating MORL methods typically generate a fixed policy…

Machine Learning · Computer Science 2025-05-09 Ruohong Liu , Yuxin Pan , Linjie Xu , Lei Song , Jiang Bian , Pengcheng You , Yize Chen

We introduce a new algorithm for multi-objective reinforcement learning (MORL) with linear preferences, with the goal of enabling few-shot adaptation to new tasks. In MORL, the aim is to learn policies over multiple competing objectives…

Machine Learning · Computer Science 2019-11-07 Runzhe Yang , Xingyuan Sun , Karthik Narasimhan

We study the problem of inverse reinforcement learning (IRL), where the learning agent recovers a reward function using expert demonstrations. Most of the existing IRL techniques make the often unrealistic assumption that the agent has…

Machine Learning · Computer Science 2021-12-20 Franck Djeumou , Murat Cubuktepe , Craig Lennon , Ufuk Topcu

Inverse reinforcement learning (IRL) enables an agent to learn complex behavior by observing demonstrations from a (near-)optimal policy. The typical assumption is that the learner's goal is to match the teacher's demonstrated behavior. In…

Machine Learning · Computer Science 2019-10-30 Sebastian Tschiatschek , Ahana Ghosh , Luis Haug , Rati Devidze , Adish Singla

While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information.…

Artificial Intelligence · Computer Science 2024-10-30 Long Tan Le , Han Shu , Tung-Anh Nguyen , Choong Seon Hong , Nguyen H. Tran

In practice, reinforcement learning (RL) agents are often trained with a possibly imperfect proxy reward function, which may lead to a human-agent alignment issue (i.e., the learned policy either converges to non-optimal performance with…

Machine Learning · Computer Science 2024-10-10 Zhaohui Jiang , Xuening Feng , Paul Weng , Yifei Zhu , Yan Song , Tianze Zhou , Yujing Hu , Tangjie Lv , Changjie Fan

We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems. However, it is generally costly and unstable to fine-tune large foundation…

Machine Learning · Computer Science 2024-10-17 Rui Yang , Xiaoman Pan , Feng Luo , Shuang Qiu , Han Zhong , Dong Yu , Jianshu Chen

We propose a distributional framework for offline Inverse Reinforcement Learning (IRL) that jointly models uncertainty over reward functions and full distributions of returns. Unlike conventional IRL approaches that recover a deterministic…

Machine Learning · Computer Science 2026-05-29 Feiyang Wu , Ye Zhao , Anqi Wu

One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods, such as RLHF, involve multiple steps, each demanding…

Machine Learning · Computer Science 2025-03-19 Siliang Zeng , Yao Liu , Huzefa Rangwala , George Karypis , Mingyi Hong , Rasool Fakoor

The aim of inverse reinforcement learning (IRL) is to infer an agent's preferences from observing their behaviour. Usually, preferences are modelled as a reward function, $R$, and behaviour is modelled as a policy, $\pi$. One of the central…

Machine Learning · Computer Science 2024-12-17 Joar Skalse , Alessandro Abate

We consider a setting for Inverse Reinforcement Learning (IRL) where the learner is extended with the ability to actively select multiple environments, observing an agent's behavior on each environment. We first demonstrate that if the…

Artificial Intelligence · Computer Science 2016-01-26 Kareem Amin , Satinder Singh

Given a dataset of expert demonstrations, inverse reinforcement learning (IRL) aims to recover a reward for which the expert is optimal. This work proposes a model-free algorithm to solve entropy-regularized IRL problem. In particular, we…

Machine Learning · Computer Science 2025-03-04 Titouan Renard , Andreas Schlaginhaufen , Tingting Ni , Maryam Kamgarpour

Large language models (LLMs) trained with Reinforcement Learning from Human Feedback (RLHF) have demonstrated remarkable capabilities, but their underlying reward functions and decision-making processes remain opaque. This paper introduces…

Computation and Language · Computer Science 2025-10-07 Jared Joselowitz , Ritam Majumdar , Arjun Jagota , Matthieu Bou , Nyal Patel , Satyapriya Krishna , Sonali Parbhoo

Multi-objective learning under user-specified preference is common in real-world problems such as multi-lingual speech recognition under fairness. In this work, we frame such a problem as a semivectorial bilevel optimization problem, whose…

Optimization and Control · Mathematics 2025-04-07 Lisha Chen , Quan Xiao , Ellen Hidemi Fukuda , Xinyi Chen , Kun Yuan , Tianyi Chen

Inverse Reinforcement Learning (IRL) and Reinforcement Learning from Human Feedback (RLHF) are pivotal methodologies in reward learning, which involve inferring and shaping the underlying reward function of sequential decision-making…

Machine Learning · Computer Science 2024-10-16 Kihyun Kim , Jiawei Zhang , Asuman Ozdaglar , Pablo A. Parrilo

Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual…

Machine Learning · Computer Science 2024-08-20 Sriyash Poddar , Yanming Wan , Hamish Ivison , Abhishek Gupta , Natasha Jaques

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Computation and Language · Computer Science 2026-03-03 Ruoxi Cheng , Haoxuan Ma , Weixin Wang , Ranjie Duan , Jiexi Liu , Xiaoshuang Jia , Simeng Qin , Xiaochun Cao , Yang Liu , Xiaojun Jia

Inverse Reinforcement Learning (IRL) has demonstrated effectiveness in a variety of imitation tasks. In this paper, we introduce an IRL framework designed to extract rewarding features from expert trajectories affected by delayed…

Machine Learning · Computer Science 2024-12-05 Simon Sinong Zhan , Qingyuan Wu , Zhian Ruan , Frank Yang , Philip Wang , Yixuan Wang , Ruochen Jiao , Chao Huang , Qi Zhu

Aligning large language models (LLMs) with human preferences is critical for enhancing LLMs' safety, helpfulness, humor, faithfulness, etc. Current reinforcement learning from human feedback (RLHF) mainly focuses on a fixed reward learned…

Machine Learning · Computer Science 2026-04-07 Qiang He , Yucheng Yang , Tianyi Zhou , Meng Fang , Mykola Pechenizkiy , Setareh Maghsudi