中文
相关论文

相关论文: A Simple Unified Uncertainty-Guided Framework for …

200 篇论文

Meta-reinforcement learning (RL) methods can meta-train policies that adapt to new tasks with orders of magnitude less data than standard RL, but meta-training itself is costly and time-consuming. If we can meta-train on offline data, then…

机器学习 · 计算机科学 2022-07-08 Vitchyr H. Pong , Ashvin Nair , Laura Smith , Catherine Huang , Sergey Levine

In offline reinforcement learning, a policy learns to maximize cumulative rewards with a fixed collection of data. Towards conservative strategy, current methods choose to regularize the behavior policy or learn a lower bound of the value…

机器学习 · 计算机科学 2021-03-02 Hongchang Zhang , Jianzhun Shao , Yuhang Jiang , Shuncheng He , Xiangyang Ji

Alignment methodologies have emerged as a critical pathway for enhancing language model alignment capabilities. While SFT (supervised fine-tuning) accelerates convergence through direct token-level loss intervention, its efficacy is…

Modern astronomical experiments are designed to achieve multiple scientific goals, from studies of galaxy evolution to cosmic acceleration. These goals require data of many different classes of night-sky objects, each of which has a…

天体物理仪器与方法 · 物理学 2023-12-01 Franco Terranova , M. Voetberg , Brian Nord , Amanda Pagul

Reinforcement learning (RL) plays a central role in improving the reasoning and alignment of large language models, yet its efficiency critically depends on how training data are selected. Existing online selection strategies predominantly…

机器学习 · 计算机科学 2026-03-03 Xinyu Zhou , Boyu Zhu , Haotian Zhang , Huiming Wang , Zhijiang Guo

Deep research agents have shown remarkable potential in handling long-horizon tasks. However, state-of-the-art performance typically relies on online reinforcement learning (RL), which is financially expensive due to extensive API calls.…

人工智能 · 计算机科学 2026-02-24 Yuhang Zhou , Kai Zheng , Qiguang Chen , Mengkang Hu , Qingfeng Sun , Can Xu , Jingjing Chen

This paper presents a comprehensive benchmarking suite tailored to offline safe reinforcement learning (RL) challenges, aiming to foster progress in the development and evaluation of safe learning algorithms in both the training and…

机器学习 · 计算机科学 2023-06-19 Zuxin Liu , Zijian Guo , Haohong Lin , Yihang Yao , Jiacheng Zhu , Zhepeng Cen , Hanjiang Hu , Wenhao Yu , Tingnan Zhang , Jie Tan , Ding Zhao

Driven by inherent uncertainty and the sim-to-real gap, robust reinforcement learning (RL) seeks to improve resilience against the complexity and variability in agent-environment sequential interactions. Despite the existence of a large…

机器学习 · 计算机科学 2025-02-28 Shangding Gu , Laixi Shi , Muning Wen , Ming Jin , Eric Mazumdar , Yuejie Chi , Adam Wierman , Costas Spanos

Ensuring reliability in modern software systems requires rigorous pre-production testing across highly heterogeneous and evolving environments. Because exhaustive evaluation is infeasible, practitioners must decide how to allocate limited…

软件工程 · 计算机科学 2025-10-08 Yu Zhu

Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-space perturbations such as actuator faults. This study…

机器人学 · 计算机科学 2026-03-02 Shingo Ayabe , Hiroshi Kera , Kazuhiko Kawamoto

Reinforcement learning (RL) has achieved remarkable success in real-world decision-making across diverse domains, including gaming, robotics, online advertising, public health, and natural language processing. Despite these advances, a…

应用统计 · 统计学 2026-01-23 Asim H. Gazi , Yongyi Guo , Daiqi Gao , Ziping Xu , Kelly W. Zhang , Susan A. Murphy

Query optimization is a crucial component for the efficacy of Retrieval-Augmented Generation (RAG) systems. While reinforcement learning (RL)-based agentic and reasoning methods have recently emerged as a promising direction on query…

人工智能 · 计算机科学 2026-01-30 Wei Wen , Sihang Deng , Tianjun Wei , Keyu Chen , Ruizhi Qiao , Xing Sun

Solving real-world complex tasks using reinforcement learning (RL) without high-fidelity simulation environments or large amounts of offline data can be quite challenging. Online RL agents trained in imperfect simulation environments can…

The goal of robust reinforcement learning (RL) is to learn a policy that is robust against the uncertainty in model parameters. Parameter uncertainty commonly occurs in many real-world RL applications due to simulator modeling errors,…

机器学习 · 计算机科学 2022-10-19 Kishan Panaganti , Zaiyan Xu , Dileep Kalathil , Mohammad Ghavamzadeh

Care coordination and population health management programs serve large Medicaid and safety-net populations and must be auditable, efficient, and adaptable. While clinical risk for outreach modalities is typically low, time and opportunity…

计算机与社会 · 计算机科学 2025-09-23 Sanjay Basu , Sadiq Y. Patel , Parth Sheth , Bhairavi Muralidharan , Namrata Elamaran , Aakriti Kinra , Rajaie Batniji

Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as to…

机器学习 · 计算机科学 2021-10-13 Ilya Kostrikov , Ashvin Nair , Sergey Levine

Existing studies have optimized retrieval-augmented generation (RAG) across various sub-tasks, such as query understanding and retrieval refinement, but integrating these optimizations into a unified framework remains challenging. To tackle…

计算与语言 · 计算机科学 2025-05-22 Yutao Zhu , Jiajie Jin , Hongjin Qian , Zheng Liu , Zhicheng Dou , Ji-Rong Wen

We present Q-chunking, a simple yet effective recipe for improving reinforcement learning (RL) algorithms for long-horizon, sparse-reward tasks. Our recipe is designed for the offline-to-online RL setting, where the goal is to leverage an…

机器学习 · 计算机科学 2026-05-12 Qiyang Li , Zhiyuan Zhou , Sergey Levine

Offline reinforcement learning (RL) methods strike a balance between exploration and exploitation by conservative value estimation -- penalizing values of unseen states and actions. Model-free methods penalize values at all unseen actions,…

机器学习 · 计算机科学 2023-09-26 Nirbhay Modhe , Qiaozi Gao , Ashwin Kalyan , Dhruv Batra , Govind Thattai , Gaurav Sukhatme

Reinforcement learning (RL) is ubiquitous in the development of modern AI systems. However, state-of-the-art RL agents require extensive, and potentially unsafe, interactions with their environments to learn effectively. These limitations…

机器学习 · 计算机科学 2025-08-01 Yarden As , Bhavya Sukhija , Lenart Treven , Carmelo Sferrazza , Stelian Coros , Andreas Krause