English
Related papers

Related papers: Learning Sampling Policy for Faster Derivative Fre…

200 papers

Reinforcement Learning (RL) offers a fundamental framework for discovering optimal action strategies through interactions within unknown environments. Recent advancement have shown that the performance and applicability of RL can…

Machine Learning · Computer Science 2024-09-04 So Nakashima , Tetsuya J. Kobayashi

Offline reinforcement learning (RL) aims to learn a policy that maximizes the expected return using a given static dataset of transitions. However, offline RL faces the distribution shift problem. The policy constraint offline RL method is…

Machine Learning · Computer Science 2025-12-24 Yuanhao Chen , Qi Liu , Pengbin Chen , Zhongjian Qiao , Yanjie Li

Zeroth-Order Optimization (ZOO) provides powerful tools for optimizing functions where explicit gradients are unavailable or expensive to compute. However, the underlying mechanisms of popular ZOO methods, particularly those employing…

Machine Learning · Computer Science 2025-06-18 Junbin Qiu , Zhengpeng Xie , Xiangda Yan , Yongjie Yang , Yao Shu

In the learning to learn (L2L) framework, we cast the design of optimization algorithms as a machine learning problem and use deep neural networks to learn the update rules. In this paper, we extend the L2L framework to zeroth-order (ZO)…

Machine Learning · Computer Science 2020-02-10 Yangjun Ruan , Yuanhao Xiong , Sashank Reddi , Sanjiv Kumar , Cho-Jui Hsieh

Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization.…

Machine Learning · Computer Science 2019-11-27 Kaixiang Lin , Jiayu Zhou

Reinforcement Learning (RL) has proven highly effective in addressing complex control and decision-making tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution, which…

Machine Learning · Computer Science 2026-04-02 Ruijie Hao , Longfei Zhang , Yang Dai , Yang Ma , Xingxing Liang , Guangquan Cheng

Single-trajectory reinforcement learning (RL) methods aim to optimize policies from datasets consisting of (prompt, response, reward) triplets, where scalar rewards are directly available. This supervision format is highly practical, as it…

Machine Learning · Computer Science 2025-12-23 Bilal Faye , Hanane Azzag , Mustapha Lebbah

Standard model-free deep reinforcement learning (RL) algorithms sample a new initial state for each trial, allowing them to optimize policies that can perform well even in highly stochastic environments. However, problems that exhibit…

Machine Learning · Computer Science 2018-04-30 Dibya Ghosh , Avi Singh , Aravind Rajeswaran , Vikash Kumar , Sergey Levine

Zeroth-order optimizers have recently emerged as a practical approach for fine-tuning large language models (LLMs), significantly reducing GPU memory consumption compared to traditional first-order methods. Yet, existing zeroth-order…

Machine Learning · Computer Science 2025-10-02 Kairun Zhang , Haoyu Li , Yanjun Zhao , Yifan Sun , Huan Zhang

The goal of reinforcement learning (RL) is to let an agent learn an optimal control policy in an unknown environment so that future expected rewards are maximized. The model-free RL approach directly learns the policy based on data samples.…

Machine Learning · Statistics 2013-07-22 Syogo Mori , Voot Tangkaratt , Tingting Zhao , Jun Morimoto , Masashi Sugiyama

Learning a predictive model of the mean return, or value function, plays a critical role in many reinforcement learning algorithms. Distributional reinforcement learning (DRL) has been shown to improve performance by modeling the value…

Machine Learning · Computer Science 2025-07-08 Ju-Seung Byun , Andrew Perrault

We introduce LOREN, a curvature-aware zeroth-order (ZO) optimization method for fine-tuning large language models (LLMs). Existing ZO methods, which estimate gradients via finite differences using random perturbations, often suffer from…

Machine Learning · Computer Science 2025-11-12 Hyunseok Seung , Jaewoo Lee , Hyunsuk Ko

In constrained reinforcement learning (C-RL), an agent seeks to learn from the environment a policy that maximizes the expected cumulative reward while satisfying minimum requirements in secondary cumulative reward constraints. Several…

Machine Learning · Computer Science 2022-12-06 Tianqi Zheng , Pengcheng You , Enrique Mallada

In this paper, we propose a distributed zeroth-order policy optimization method for Multi-Agent Reinforcement Learning (MARL). Existing MARL algorithms often assume that every agent can observe the states and actions of all the other agents…

Machine Learning · Computer Science 2023-06-21 Yan Zhang , Michael M. Zavlanos

A major challenge of applying zeroth-order (ZO) methods is the high query complexity, especially when queries are costly. We propose a novel gradient estimation technique for ZO methods based on adaptive lazy queries that we term as LAZO.…

Machine Learning · Computer Science 2022-06-16 Quan Xiao , Qing Ling , Tianyi Chen

In collaborative human-robot order picking systems, human pickers and Autonomous Mobile Robots (AMRs) travel independently through a warehouse and meet at pick locations where pickers load items onto the AMRs. In this paper, we consider an…

Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. While traditional RL methods aim to learn a point estimate of the random cumulative cost, distributional RL (DRL) seeks…

Machine Learning · Computer Science 2025-02-03 Minheng Xiao , Xian Yu , Lei Ying

Fine-tuning large language models (LLMs) using standard first-order (FO) optimization often drives training toward sharp, poorly generalizing minima. Conversely, zeroth-order (ZO) methods offer stronger exploratory behavior without relying…

Machine Learning · Computer Science 2026-01-12 Feihu Jin , Ying Tan

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications. Previous primal-dual style approaches suffer from instability issues and lack optimality…

Machine Learning · Computer Science 2022-06-20 Zuxin Liu , Zhepeng Cen , Vladislav Isenbaev , Wei Liu , Zhiwei Steven Wu , Bo Li , Ding Zhao

Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for sample reuse. In this paper, we show that the use of…

Machine Learning · Computer Science 2023-02-07 Zichuan Lin , Xiapeng Wu , Mingfei Sun , Deheng Ye , Qiang Fu , Wei Yang , Wei Liu