English
Related papers

Related papers: Beyond Precision: Training-Inference Mismatch is a…

200 papers

We focus on the task of approximating the optimal value function in deep reinforcement learning. This iterative process is comprised of solving a sequence of optimization problems where the loss function changes per iteration. The common…

Machine Learning · Computer Science 2023-11-16 Kavosh Asadi , Rasool Fakoor , Shoham Sabach

Reinforcement learning has seen wide success in finetuning large language models to better align with instructions via human feedback. The so-called algorithm, Reinforcement Learning with Human Feedback (RLHF) demonstrates impressive…

Computation and Language · Computer Science 2023-02-13 Tianjun Zhang , Fangchen Liu , Justin Wong , Pieter Abbeel , Joseph E. Gonzalez

In this work, we present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM), addressing its limited generalization compared to reinforcement learning (RL). Through…

Machine Learning · Computer Science 2026-03-02 Yongliang Wu , Yizhou Zhou , Zhou Ziheng , Yingzhe Peng , Xinyu Ye , Xinting Hu , Wenbo Zhu , Lu Qi , Ming-Hsuan Yang , Xu Yang

Setting the learning rate (LR) for a deep learning model is a critical part of successful training. Choosing LRs is often done empirically with trial and error. In this work, we explore a solvable model of optimal LR schedules for a…

Disordered Systems and Neural Networks · Physics 2026-05-11 Blake Bordelon , Francesco Mori

Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories. Classical (dual-ascent) IRL guarantees monotonic performance improvement but requires fully…

Machine Learning · Computer Science 2026-05-13 Anish Diwan , Davide Tateo , Christopher E. Mower , Haitham Bou-Ammar , Jan Peters , Oleg Arenz

Fine-tuning foundation models via reinforcement learning (RL) has proven promising for aligning to downstream objectives. In the case of diffusion models (DMs), though RL training improves alignment from early timesteps, critical issues…

Machine Learning · Statistics 2024-10-14 Roberto Barceló , Cristóbal Alcázar , Felipe Tobar

The availability of large pre-trained models is changing the landscape of Machine Learning research and practice, moving from a training-from-scratch to a fine-tuning paradigm. While in some applications the goal is to "nudge" the…

Machine Learning · Computer Science 2022-11-15 Tomasz Korbak , Hady Elsahar , Germán Kruszewski , Marc Dymetman

In this paper, a deep reinforcement learning (DRL) method is proposed to address the problem of UAV navigation in an unknown environment. However, DRL algorithms are limited by the data efficiency problem as they typically require a huge…

Robotics · Computer Science 2020-08-07 Lei He , Nabil Aouf , James F. Whidborne , Bifeng Song

Building deep reinforcement learning (RL) agents that find a good policy with few samples has proven notoriously challenging. To achieve sample efficiency, recent work has explored updating neural networks with large numbers of gradient…

Machine Learning · Computer Science 2025-04-04 Claas A Voelcker , Marcel Hussing , Eric Eaton , Amir-massoud Farahmand , Igor Gilitschenski

In-context learning with large language models (LLMs) excels at adapting to various tasks rapidly. However, its success hinges on carefully selecting demonstrations, which remains an obstacle in practice. Current approaches to this problem…

Computation and Language · Computer Science 2024-01-15 Shangqing Xu , Chao Zhang

Residual Reinforcement Learning (RL) is a popular approach for adapting pretrained policies by learning a lightweight residual policy that provides corrective actions. While Residual RL is more sample-efficient than finetuning the entire…

Machine Learning · Computer Science 2026-03-16 Lakshita Dodeja , Karl Schmeckpeper , Shivam Vats , Thomas Weng , Mingxi Jia , George Konidaris , Stefanie Tellex

Large-batch training has been essential in leveraging large-scale datasets and models in deep learning. While it is computationally beneficial to use large batch sizes, it often requires a specially designed learning rate (LR) schedule to…

Machine Learning · Computer Science 2021-07-14 Chiheon Kim , Saehoon Kim , Jongmin Kim , Donghoon Lee , Sungwoong Kim

Reinforcement learning (RL) for large language model reasoning is frequently hindered by signal loss, a phenomenon where standard uniform sampling with small group sizes fails to uncover informative learning signals for difficult prompts.…

Machine Learning · Computer Science 2025-12-08 Wei Xiong , Chenlu Ye , Baohao Liao , Hanze Dong , Xinxing Xu , Christof Monz , Jiang Bian , Nan Jiang , Tong Zhang

In recent years, by leveraging more data, computation, and diverse tasks, learned optimizers have achieved remarkable success in supervised learning, outperforming classical hand-designed optimizers. Reinforcement learning (RL) is…

Machine Learning · Computer Science 2024-06-05 Qingfeng Lan , A. Rupam Mahmood , Shuicheng Yan , Zhongwen Xu

Reinforcement learning (RL) has shown promise in solving various combinatorial optimization problems. However, conventional RL faces challenges when dealing with complex, real-world constraints, especially when action space feasibility is…

Machine Learning · Computer Science 2025-08-12 Jaike van Twiller , Yossiri Adulyasak , Erick Delage , Djordje Grbic , Rune Møller Jensen

When adapting ICL with or without fine-tuning, we are curious about whether the instruction-tuned language model is able to achieve well-calibrated results without suffering from the problem of overconfidence (i.e., miscalibration)…

Computation and Language · Computer Science 2025-05-23 Chengzu Li , Han Zhou , Goran Glavaš , Anna Korhonen , Ivan Vulić

The endeavor of artificial intelligence (AI) is to design autonomous agents capable of achieving complex tasks. Namely, reinforcement learning (RL) proposes a theoretical background to learn optimal behaviors. In practice, RL algorithms…

Machine Learning · Computer Science 2022-09-27 Firas Jarboui , Ahmed Akakzia

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Machine Learning · Computer Science 2026-01-27 Lianlei Shan , Han Chen , Yixuan Wang , Zhenjie Liu , Wei Li

Finetuning large language models on narrowly harmful datasets can cause them to become emergently misaligned, giving stereotypically `evil' responses across diverse unrelated settings. Concerningly, a pre-registered survey of experts failed…

Artificial Intelligence · Computer Science 2026-02-10 Anna Soligo , Edward Turner , Senthooran Rajamanoharan , Neel Nanda

We investigate the problem of machine learning with mislabeled training data. We try to make the effects of mislabeled training better understood through analysis of the basic model and equations that characterize the problem. This includes…

Machine Learning · Computer Science 2019-09-23 Herbert Gish , Jan Silovsky , Man-Ling Sung , Man-Hung Siu , William Hartmann , Zhuolin Jiang