English
Related papers

Related papers: RL's Razor: Why Online Reinforcement Learning Forg…

200 papers

This work revisits the dominant supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm for training Large Vision-Language Models (LVLMs), and reveals a key finding: SFT can significantly undermine subsequent RL by inducing…

Computation and Language · Computer Science 2025-04-17 Hardy Chen , Haoqin Tu , Fali Wang , Hui Liu , Xianfeng Tang , Xinya Du , Yuyin Zhou , Cihang Xie

Online matching problems arise in many complex systems, from cloud services and online marketplaces to organ exchange networks, where timely, principled decisions are critical for maintaining high system performance. Traditional heuristics…

Machine Learning · Statistics 2025-10-09 Chiara Mignacco , Matthieu Jonckheere , Gilles Stoltz

Test-time scaling methods have seen a rapid increase in popularity for its computational efficiency and parameter-independent training to improve reasoning performance on Large Language Models. One such method is called budget forcing, a…

Artificial Intelligence · Computer Science 2025-10-27 Ravindra Aribowo Tarunokusumo , Rafael Fernandes Cunha

After the pretraining stage of LLMs, techniques such as SFT, RLHF, RLVR, and RFT are applied to enhance instruction-following ability, mitigate undesired responses, improve reasoning capability and enable efficient domain adaptation with…

Computation and Language · Computer Science 2025-10-17 Zhichao Wang , Andy Wong , Ruslan Belkin

Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks. Despite the substantial empirical gains demonstrated by RL-based training methods like GRPO, a…

Artificial Intelligence · Computer Science 2025-10-27 Jiayu Wang , Yifei Ming , Zixuan Ke , Caiming Xiong , Shafiq Joty , Aws Albarghouthi , Frederic Sala

Recently, robust reinforcement learning (RL) methods against input observation have garnered significant attention and undergone rapid evolution due to RL's potential vulnerability. Although these advanced methods have achieved reasonable…

Machine Learning · Computer Science 2024-09-04 Kosuke Nakanishi , Akihiro Kubo , Yuji Yasui , Shin Ishii

In sequential decision-making problems, Return-Conditioned Supervised Learning (RCSL) has gained increasing recognition for its simplicity and stability in modern decision-making tasks. Unlike traditional offline reinforcement learning (RL)…

Machine Learning · Computer Science 2025-06-11 Zhishuai Liu , Yu Yang , Ruhan Wang , Pan Xu , Dongruo Zhou

Reinforcement learning (RL) algorithms have demonstrated promising results on complex tasks, yet often require impractical numbers of samples since they learn from scratch. Meta-RL aims to address this challenge by leveraging experience…

Machine Learning · Computer Science 2020-10-28 Russell Mendonca , Abhishek Gupta , Rosen Kralev , Pieter Abbeel , Sergey Levine , Chelsea Finn

Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time. However, we can also view RL as a generic sequence modeling problem,…

Machine Learning · Computer Science 2021-11-30 Michael Janner , Qiyang Li , Sergey Levine

A promising paradigm for offline reinforcement learning (RL) is to constrain the learned policy to stay close to the dataset behaviors, known as policy constraint offline RL. However, existing works heavily rely on the purity of the data,…

Machine Learning · Computer Science 2022-10-20 Chengqian Gao , Ke Xu , Liu Liu , Deheng Ye , Peilin Zhao , Zhiqiang Xu

Deep Reinforcement Learning (RL) methods rely on experience replay to approximate the minibatched supervised learning setting; however, unlike supervised learning where access to lots of training data is crucial to generalization,…

Machine Learning · Computer Science 2021-02-24 Brett Daley , Cameron Hickert , Christopher Amato

One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution. Whether the data originates from a near-optimal policy or not, we anticipate that an algorithm should demonstrate its…

Machine Learning · Computer Science 2023-10-18 Xiaohan Hu , Yi Ma , Chenjun Xiao , Yan Zheng , Jianye Hao

Executing workflows on volunteer computing resources where individual tasks may be forced to relinquish their resource for the resource's primary use leads to unpredictability and often significantly increases execution time. Task…

Performance · Computer Science 2022-09-28 Andrew Stephen McGough , Matthew Forshaw

Frontier models have demonstrated exceptional capabilities following the integration of task-reward-based reinforcement learning (RL) into their training pipelines, enabling systems to evolve from pure reasoning models into sophisticated…

Machine Learning · Computer Science 2026-04-20 Sarthak Mittal , Leo Gagnon , Guillaume Lajoie

In many real-world settings, reinforcement learning systems suffer performance degradation when the environment encountered at deployment differs from that observed during training. Distributionally robust reinforcement learning (DR-RL)…

Machine Learning · Computer Science 2026-03-05 Debamita Ghosh , George K. Atia , Yue Wang

Much attention has been devoted recently to the development of machine learning algorithms with the goal of improving treatment policies in healthcare. Reinforcement learning (RL) is a sub-field within machine learning that is concerned…

Reinforcement Learning (RL) is a method for learning decision-making tasks that could enable robots to learn and adapt to their situation on-line. For an RL algorithm to be practical for robotic control tasks, it must learn in very few…

Artificial Intelligence · Computer Science 2015-03-19 Todd Hester , Michael Quinlan , Peter Stone

Fine-tuning reinforcement learning (RL) models has been challenging because of a lack of large scale off-the-shelf datasets as well as high variance in transferability among different environments. Recent work has looked at tackling offline…

Machine Learning · Computer Science 2022-07-26 Machel Reid , Yutaro Yamada , Shixiang Shane Gu

Fine-tuning adapts a pre-trained model to downstream tasks using a small amount of labeled data. Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that reduces memory and computation costs while often achieving performance close…

Machine Learning · Computer Science 2026-05-20 Ali Zindari , Rotem Mulayoff , Sebastian U. Stich

This paper bridges some of the gap between optimal planning and reinforcement learning (RL), both of which share roots in dynamic programming applied to sequential decision making or optimal control. Whereas planning typically favors…

Robotics · Computer Science 2026-03-10 Filip V. Georgiev , Kalle G. Timperi , Başak Sakçak , Steven M. LaValle