English
Related papers

Related papers: Internalizing Curriculum Judgment for LLM Reinforc…

200 papers

In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. However, current meta-RL approaches rely on manually-defined…

Artificial Intelligence · Computer Science 2019-12-10 Allan Jabri , Kyle Hsu , Ben Eysenbach , Abhishek Gupta , Sergey Levine , Chelsea Finn

Parameter-efficient fine-tuning (PEFT) of pre-trained language models (PLMs) has emerged as a highly successful approach, with training only a small number of parameters without sacrificing performance and becoming the de-facto learning…

Computation and Language · Computer Science 2023-10-20 Baohao Liao , Shaomu Tan , Christof Monz

Existing test-time scaling (TTS) methods for unified multimodal models (UMMs) in text-to-image (T2I) generation primarily rely on search or sampling strategies that produce only instance-level improvements, limiting the ability to learn…

Machine Learning · Computer Science 2026-03-18 Lit Sin Tan , Junzhe Chen , Xiaolong Fu , Lichen Ma , Junshi Huang , Jianzhong Shi , Yan Li , Lijie Wen

Deep reinforcement learning includes a broad family of algorithms that parameterise an internal representation, such as a value function or policy, by a deep neural network. Each algorithm optimises its parameters with respect to an…

Machine Learning · Computer Science 2020-07-17 Zhongwen Xu , Hado van Hasselt , Matteo Hessel , Junhyuk Oh , Satinder Singh , David Silver

Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mystery how rewards based solely on final outcomes can help overcome the long-horizon barrier…

Machine Learning · Computer Science 2026-05-07 Yu Huang , Zixin Wen , Yuejie Chi , Yuting Wei , Aarti Singh , Yingbin Liang , Yuxin Chen

Incorporating high-level knowledge is an effective way to expedite reinforcement learning (RL), especially for complex tasks with sparse rewards. We investigate an RL problem where the high-level knowledge is in the form of reward machines,…

Artificial Intelligence · Computer Science 2022-02-10 Zhe Xu , Ivan Gavran , Yousef Ahmad , Rupak Majumdar , Daniel Neider , Ufuk Topcu , Bo Wu

Recent studies have demonstrated the effectiveness of LLM test-time scaling. However, existing approaches to incentivize LLMs' deep thinking abilities generally require large-scale data or significant training efforts. Meanwhile, it remains…

Computation and Language · Computer Science 2025-02-19 Ruotian Ma , Peisong Wang , Cheng Liu , Xingyan Liu , Jiaqi Chen , Bang Zhang , Xin Zhou , Nan Du , Jia Li

Supervised open-loop training has been widely adopted for training traffic simulation models; however, it fails to capture the inherently dynamic, multi-agent interactions common in complex driving scenarios. We introduce RLFTSim, a…

Training on large amounts of rationales (i.e., CoT Fine-tuning) is effective at improving the reasoning capabilities of large language models (LLMs). However, acquiring human-authored rationales or augmenting rationales from proprietary…

Computation and Language · Computer Science 2024-10-04 Hyeonbin Hwang , Doyoung Kim , Seungone Kim , Seonghyeon Ye , Minjoon Seo

Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. However, prompting often leads models to make predictions with lower accuracy compared to finetuning a model…

Computation and Language · Computer Science 2024-08-13 Chenyang Zhao , Xueying Jia , Vijay Viswanathan , Tongshuang Wu , Graham Neubig

We propose an adaptation of the curriculum training framework, applicable to state-of-the-art meta learning techniques for few-shot classification. Curriculum-based training popularly attempts to mimic human learning by progressively…

Machine Learning · Computer Science 2021-12-07 Emmanouil Stergiadis , Priyanka Agrawal , Oliver Squire

Leveraging the model's internal information as the self-reward signal in Reinforcement Learning (RL) has received extensive attention due to its label-free nature. While prior works have made significant progress in applying the Test-Time…

Machine Learning · Computer Science 2026-03-18 Xizhong Yang , Yinan Xia , Huiming Wang , Mofei Song

This work proposes `PET', a novel pessimistic reward fine-tuning method, to learn a pessimistic reward model robust against reward hacking in offline reinforcement learning from human feedback (RLHF). Traditional reward modeling techniques…

Machine Learning · Computer Science 2025-05-28 Yinglun Xu , Hangoo Kang , Tarun Suresh , Yuxuan Wan , Gagandeep Singh

Reinforcement learning (RL) has enhanced the capabilities of large language models (LLMs) through reward-driven training. Nevertheless, this process can introduce excessively long responses, inflating inference latency and computational…

Machine Learning · Computer Science 2026-02-17 Chang Liu , Yiran Zhao , Lawrence Liu , Yaoqi Ye , Csaba Szepesvári , Lin F. Yang

From a first-principles perspective, it may seem odd that the strongest results in foundation model fine-tuning (FT) are achieved via a relatively complex, two-stage training procedure. Specifically, one first trains a reward model (RM) on…

Machine Learning · Computer Science 2025-10-20 Gokul Swamy , Sanjiban Choudhury , Wen Sun , Zhiwei Steven Wu , J. Andrew Bagnell

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…

Computation and Language · Computer Science 2024-06-18 Zhipeng Chen , Kun Zhou , Wayne Xin Zhao , Junchen Wan , Fuzheng Zhang , Di Zhang , Ji-Rong Wen

Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL). But conventional approaches rely on outcome-only rewards that provide sparse feedback, resulting in…

Machine Learning · Computer Science 2025-08-01 Tao He , Rongchuan Mu , Lizi Liao , Yixin Cao , Ming Liu , Bing Qin

Many challenging reinforcement learning (RL) problems require designing a distribution of tasks that can be applied to train effective policies. This distribution of tasks can be specified by the curriculum. A curriculum is meant to improve…

Machine Learning · Computer Science 2023-01-03 Maria Nesterova , Alexey Skrynnik , Aleksandr Panov

Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs). In the multiple-choice setting - a dominant format for multimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Jiahao Wang , Weiye Xu , Aijun Yang , Wengang Zhou , Lewei Lu , Houqiang Li , Xiaohua Wang , Jinguo Zhu

Despite ample motivation from costly exploration and limited trajectory data, rapidly adapting to new environments with few-shot reinforcement learning (RL) can remain a challenging task, especially with respect to personalized settings.…

Machine Learning · Computer Science 2020-10-13 Michael Zhang
‹ Prev 1 8 9 10 Next ›