English
Related papers

Related papers: Exploration via linearly perturbed loss minimisati…

200 papers

The piecewise-stationary bandit problem is an important variant of the multi-armed bandit problem that further considers abrupt changes in the reward distributions. The main theme of the problem is the trade-off between exploration for…

Machine Learning · Computer Science 2024-10-10 Kuan-Ta Li , Ping-Chun Hsieh , Yu-Chih Huang

We consider online learning problems under a partial observability model capturing situations where the information conveyed to the learner is between full information and bandit feedback. In the simplest variant, we assume that in addition…

Machine Learning · Computer Science 2026-04-28 Tomas Kocak , Gergely Neu , Michal Valko , Remi Munos

We study the problem of offline learning in automated decision systems under the contextual bandits model. We are given logged historical data consisting of contexts, (randomized) actions, and (nonnegative) rewards. A common goal is to…

Machine Learning · Computer Science 2019-01-16 Yifei Ma , Yu-Xiang Wang , Balakrishnan , Narayanaswamy

Collecting web data to train deep models has become increasingly common, raising concerns about unauthorized data usage. To mitigate this issue, unlearnable examples introduce imperceptible perturbations into data, preventing models from…

Machine Learning · Computer Science 2026-01-30 Jinlin Liu , Wei Chen , Xiaojin Zhang

Real-world contextual bandit problems with complex reward models are often tackled with iteratively trained models, such as boosting trees. However, it is difficult to directly apply simple and effective exploration strategies--such as…

We introduce Random Latent Exploration (RLE), a simple yet effective exploration strategy in reinforcement learning (RL). On average, RLE outperforms noise-based methods, which perturb the agent's actions, and bonus-based exploration, which…

Machine Learning · Computer Science 2025-02-28 Srinath Mahankali , Zhang-Wei Hong , Ayush Sekhari , Alexander Rakhlin , Pulkit Agrawal

Exploration in reinforcement learning (RL) remains an open challenge. RL algorithms rely on observing rewards to train the agent, and if informative rewards are sparse the agent learns slowly or may not learn at all. To improve exploration…

Machine Learning · Computer Science 2024-11-12 Simone Parisi , Alireza Kazemipour , Michael Bowling

The combinatorial pure exploration of causal bandits is the following online learning task: given a causal graph with unknown causal inference distributions, in each round we choose a subset of variables to intervene or do no intervention,…

Machine Learning · Computer Science 2023-03-15 Nuoya Xiong , Wei Chen

We propose and analyze TRAiL (Tangential Randomization in Linear Bandits), a computationally efficient regret-optimal forced exploration algorithm for linear bandits on action sets that are sublevel sets of strongly convex functions. TRAiL…

Machine Learning · Statistics 2024-11-20 Arda Güçlü , Subhonmesh Bose

Psychological research shows that enjoyment of many goods is subject to satiation, with short-term satisfaction declining after repeated exposures to the same item. Nevertheless, proposed algorithms for powering recommender systems seldom…

Machine Learning · Computer Science 2021-10-28 Liu Leqi , Fatma Kilinc-Karzan , Zachary C. Lipton , Alan L. Montgomery

In stochastic multi-armed bandits, a major problem the learner faces is the trade-off between exploration and exploitation. Recently, exploration-free methods -- methods that commit to the action predicted to return the highest reward --…

Machine Learning · Computer Science 2025-04-08 Jonathan Gornet , Yilin Mo , Bruno Sinopoli

We study a class of adversarial bandit optimization problems in which the loss functions may be non-convex and non-smooth. In each round, the learner observes a loss that consists of an underlying linear component together with an…

Machine Learning · Computer Science 2026-03-30 Zhuoyu Cheng , Kohei Hatano , Eiji Takimoto

Reward-biased maximum likelihood estimation (RBMLE) is a classic principle in the adaptive control literature for tackling explore-exploit trade-offs. This paper studies the stochastic contextual bandit problem with general bounded reward…

Machine Learning · Computer Science 2022-05-31 Yu-Heng Hung , Ping-Chun Hsieh

In this paper, we investigate preference-based reinforcement learning (PbRL), which enables reinforcement learning (RL) agents to learn from human feedback. This is particularly valuable when defining a fine-grain reward function is not…

Machine Learning · Computer Science 2025-11-11 Guojian Wang , Jianxiang Liu , Xinyuan Li , Faguo Wu , Xiao Zhang , Tianyuan Chen , Xuyang Chen

We develop a probabilistic framework for analysing model-based reinforcement learning in the episodic setting. We then apply it to study finite-time horizon stochastic control problems with linear dynamics but unknown coefficients and…

Machine Learning · Computer Science 2021-12-22 Lukasz Szpruch , Tanut Treetanthiploet , Yufei Zhang

In large-scale unconstrained optimization algorithms such as limited memory BFGS (LBFGS), a common subproblem is a line search minimizing the loss function along a descent direction. Commonly used line searches iteratively find an…

Numerical Analysis · Mathematics 2016-01-27 Michael B Hynes , Hans De Sterck

We study the problem of stochastic combinatorial pure exploration (CPE), where an agent sequentially pulls a set of single arms (a.k.a. a super arm) and tries to find the best super arm. Among a variety of problem settings of the CPE, we…

Machine Learning · Computer Science 2021-10-26 Yuko Kuroki , Liyuan Xu , Atsushi Miyauchi , Junya Honda , Masashi Sugiyama

Efficient robotic exploration of unknown, sensor limited, global-information-deficient environments poses unique challenges to path planning algorithms. In these difficult environments, no deterministic guarantees on path completion and…

Robotics · Computer Science 2017-05-01 Alexander Ivanov , Mark Campbell

We investigate two perturbation approaches to overcome conservatism that optimism based algorithms chronically suffer from in practice. The first approach replaces optimism with a simple randomization when using confidence sets. The second…

Machine Learning · Statistics 2021-10-13 Baekjin Kim , Ambuj Tewari

We investigate how perturbation does and does not improve the Follow-the-Regularized-Leader (FTRL) algorithm in solving imperfect-information extensive-form games under sampling, where payoffs are estimated from sampled trajectories. While…

Computer Science and Game Theory · Computer Science 2025-08-05 Wataru Masaka , Mitsuki Sakamoto , Kenshi Abe , Kaito Ariu , Tuomas Sandholm , Atsushi Iwasaki