English
Related papers

Related papers: Exploration via linearly perturbed loss minimisati…

200 papers

This paper bridges reinforcement learning (RL) and risk-sensitive stochastic control by introducing a tractable exploration mechanism for policy search in risk-sensitive portfolio management, with known and unknown model parameters, that…

Portfolio Management · Quantitative Finance 2026-03-03 Sebastien Lleo , Wolfgang Runggaldier

Numerous machine learning problems require an exploration basis - a mechanism to explore the action space. We define a novel geometric notion of exploration basis with low variance, called volumetric spanners, and give efficient algorithms…

Machine Learning · Computer Science 2014-05-27 Elad Hazan , Zohar Karnin , Raghu Mehka

LLM-guided evolutionary search (Evolve systems) has reached state-of-the-art results on mathematical and combinatorial tasks, yet most existing systems report only the best of many runs and leave the run-to-run distribution undocumented. We…

Computation and Language · Computer Science 2026-05-29 Sixue Xing , Haoyu He , Kerui Wu , Zhuo Yang , Haozheng Luo , Tianfan Fu , Aarthy Nagarajan

Verifying whether the machine unlearning process has been properly executed is critical but remains underexplored. Some existing approaches propose unlearning verification methods based on backdooring techniques. However, these methods…

Machine Learning · Computer Science 2026-02-04 Weiqi Wang , Zhiyi Tian , Chenhan Zhang , Luoyu Chen , Shui Yu

This paper examines the exploration-exploitation trade-off in reinforcement learning with verifiable rewards (RLVR), a framework for improving the reasoning of Large Language Models (LLMs). Recent studies suggest that RLVR can elicit strong…

Machine Learning · Computer Science 2026-01-27 Peter Chen , Xiaopeng Li , Ziniu Li , Wotao Yin , Xi Chen , Tianyi Lin

In this work, we address the challenge of data-efficient exploration in reinforcement learning by examining existing principled, information-theoretic approaches to intrinsic motivation. Specifically, we focus on a class of exploration…

Machine Learning · Computer Science 2025-07-04 Alberto Caron , Chris Hicks , Vasilios Mavroudis

The celebrated multi-armed bandit problem in decision theory models the basic trade-off between exploration, or learning about the state of a system, and exploitation, or utilizing the system. In this paper we study the variant of the…

Data Structures and Algorithms · Computer Science 2013-06-19 Sudipto Guha , Kamesh Munagala

Stochastic linear bandits are a natural and simple generalisation of finite-armed bandits with numerous practical applications. Current approaches focus on generalising existing techniques for finite-armed bandits, notably the optimism…

Machine Learning · Statistics 2016-10-17 Tor Lattimore , Csaba Szepesvari

Ensembling is now recognized as an effective approach for increasing the predictive performance and calibration of deep networks. We introduce a new approach, Parameter Ensembling by Perturbation (PEP), that constructs an ensemble of…

Machine Learning · Computer Science 2020-10-27 Alireza Mehrtash , Purang Abolmaesumi , Polina Golland , Tina Kapur , Demian Wassermann , William M. Wells

Many robotic exploration algorithms rely on graph structures for frontier-based exploration and dynamic path planning. However, these graphs grow rapidly, accumulating redundant information and impacting performance. We present a…

Robotics · Computer Science 2026-04-21 Adithya V. Sastry , Bibek Poudel , Weizi Li

Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences…

Machine Learning · Computer Science 2026-04-06 Yiqin Yang , Hao Hu , Yihuan Mao , Jin Zhang , Chengjie Wu , Yuhua Jiang , Xu Yang , Runpeng Xie , Yi Fan , Bo Liu , Yang Gao , Bo Xu , Chongjie Zhang

We propose a model-free reinforcement learning algorithm inspired by the popular randomized least squares value iteration (RLSVI) algorithm as well as the optimism principle. Unlike existing upper-confidence-bound (UCB) based approaches,…

Machine Learning · Computer Science 2021-10-27 Haque Ishfaq , Qiwen Cui , Viet Nguyen , Alex Ayoub , Zhuoran Yang , Zhaoran Wang , Doina Precup , Lin F. Yang

In this paper, we consider stochastic multi-armed bandits (MABs) with heavy-tailed rewards, whose $p$-th moment is bounded by a constant $\nu_{p}$ for $1<p\leq2$. First, we propose a novel robust estimator which does not require $\nu_{p}$…

Machine Learning · Computer Science 2021-10-28 Kyungjae Lee , Hongjun Yang , Sungbin Lim , Songhwai Oh

Exploration is a fundamental aspect of reinforcement learning (RL), and its effectiveness is a deciding factor in the performance of RL algorithms, especially when facing sparse extrinsic rewards. Recent studies have shown the effectiveness…

Machine Learning · Computer Science 2023-05-19 Shanchuan Wan , Yujin Tang , Yingtao Tian , Tomoyuki Kaneko

Pure exploration (aka active testing) is the fundamental task of sequentially gathering information to answer a query about a stochastic environment. Good algorithms make few mistakes and take few samples. Lower bounds (for multi-armed…

Machine Learning · Statistics 2019-06-26 Rémy Degenne , Wouter M. Koolen , Pierre Ménard

As an effective nonparametric method, empirical likelihood (EL) is appealing in combining estimating equations flexibly and adaptively for incorporating data information. To select important variables and estimating equations in the sparse…

Methodology · Statistics 2021-07-02 Jiaqi Li , Liya Fu

Conveying complex objectives to reinforcement learning (RL) agents often requires meticulous reward engineering. Preference-based RL methods are able to learn a more flexible reward model based on human preferences by actively incorporating…

Machine Learning · Computer Science 2022-05-26 Xinran Liang , Katherine Shu , Kimin Lee , Pieter Abbeel

Model-based reinforcement learning algorithms with probabilistic dynamical models are amongst the most data-efficient learning methods. This is often attributed to their ability to distinguish between epistemic and aleatoric uncertainty.…

Machine Learning · Computer Science 2020-12-02 Sebastian Curi , Felix Berkenkamp , Andreas Krause

We study the excess risk evaluation of classical penalized empirical risk minimization (ERM) with Bregman losses. We show that by leveraging the idea of wild refitting, one can efficiently upper bound the excess risk through the so-called…

Machine Learning · Statistics 2025-11-25 Haichen Hu , David Simchi-Levi

Reinforcement learning (RL) has emerged as a powerful method for improving the reasoning abilities of large language models (LLMs). Outcome-based RL, which rewards policies solely for the correctness of the final answer, yields substantial…

Machine Learning · Computer Science 2025-09-09 Yuda Song , Julia Kempe , Remi Munos