English
Related papers

Related papers: Sample-Efficiency in Multi-Batch Reinforcement Lea…

200 papers

To overcome the sim-to-real gap in reinforcement learning (RL), learned policies must maintain robustness against environmental uncertainties. While robust RL has been widely studied in single-agent regimes, in multi-agent environments, the…

Machine Learning · Computer Science 2024-05-10 Laixi Shi , Eric Mazumdar , Yuejie Chi , Adam Wierman

The recent work by Dong & Yang (2023) showed for misspecified sparse linear bandits, one can obtain an $O\left(\epsilon\right)$-optimal policy using a polynomial number of samples when the sparsity is a constant, where $\epsilon$ is the…

Machine Learning · Computer Science 2024-07-19 Ally Yalei Du , Lin F. Yang , Ruosong Wang

Exploration is a key challenge in Reinforcement Learning, especially in long-horizon, deceptive and sparse-reward environments. For such applications, population-based approaches have proven effective. Methods such as Quality-Diversity…

Neural and Evolutionary Computing · Computer Science 2022-11-24 Bryan Lim , Manon Flageat , Antoine Cully

We use a formal correspondence between thermodynamics and inference, where the number of samples can be thought of as the inverse temperature, to study a quantity called ``learning capacity'' which is a measure of the effective…

Machine Learning · Computer Science 2024-10-22 Daiwei Chen , Wei-Kai Chang , Pratik Chaudhari

This paper considers a class of reinforcement learning problems, which involve systems with two types of states: stochastic and pseudo-stochastic. In such systems, stochastic states follow a stochastic transition kernel while the…

Machine Learning · Computer Science 2023-11-09 Honghao Wei , Xin Liu , Weina Wang , Lei Ying

The reasoning ability of large language models (LLMs) can be unleashed with reinforcement learning (RL) (OpenAI, 2024; DeepSeek-AI et al., 2025a; Zeng et al., 2025). The success of existing RL attempts in LLMs usually rely on high-quality…

Machine Learning · Computer Science 2026-04-03 Yiyuan Li , Zhen Huang , Yanan Wu , Weixun Wang , Xuefeng Li , Yijia Luo , Wenbo Su , Bo Zheng , Pengfei Liu

Adaptivity is an important feature of data analysis---the choice of questions to ask about a dataset often depends on previous interactions with the same dataset. However, statistical validity is typically studied in a nonadaptive model,…

Machine Learning · Computer Science 2015-11-10 Raef Bassily , Kobbi Nissim , Adam Smith , Thomas Steinke , Uri Stemmer , Jonathan Ullman

Reinforcement learning has achieved significant milestones, but sample efficiency remains a bottleneck for real-world applications. Recently, CrossQ has demonstrated state-of-the-art sample efficiency with a low update-to-data (UTD) ratio…

Machine Learning · Computer Science 2025-05-23 Daniel Palenicek , Florian Vogt , Joe Watson , Jan Peters

Despite recent progress in robot learning, it still remains a challenge to program a robot to deal with open-ended object manipulation tasks. One approach that was recently used to autonomously generate a repertoire of diverse skills is a…

Artificial Intelligence · Computer Science 2020-08-12 Leon Keller , Daniel Tanneberg , Svenja Stark , Jan Peters

Online reinforcement learning and other adaptive sampling algorithms are increasingly used in digital intervention experiments to optimize treatment delivery for users over time. In this work, we focus on longitudinal user data collected by…

Machine Learning · Computer Science 2023-04-20 Kelly W. Zhang , Lucas Janson , Susan A. Murphy

We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample domains, but where we have many samples in each domain. Our…

Machine Learning · Computer Science 2011-05-05 Dean Foster , Sham Kakade , Ruslan Salakhutdinov

The assumption that training and testing samples are generated from the same distribution does not always hold for real-world machine-learning applications. The procedure of tackling this discrepancy between the training (source) and…

Machine Learning · Computer Science 2018-12-05 Debasmit Das , C. S. George Lee

The sample-inefficiency problem in Artificial Intelligence refers to the inability of current Deep Reinforcement Learning models to optimize action policies within a small number of episodes. Recent studies have tried to overcome this…

Artificial Intelligence · Computer Science 2020-12-29 Ismael T. Freire , Adrián F. Amil , Vasiliki Vouloutsi , Paul F. M. J. Verschure

We introduce the notion of a reproducible algorithm in the context of learning. A reproducible learning algorithm is resilient to variations in its samples -- with high probability, it returns the exact same output when run on two samples…

Machine Learning · Computer Science 2023-04-17 Russell Impagliazzo , Rex Lei , Toniann Pitassi , Jessica Sorrell

We consider the question of learning $Q$-function in a sample efficient manner for reinforcement learning with continuous state and action spaces under a generative model. If $Q$-function is Lipschitz continuous, then the minimal sample…

Machine Learning · Computer Science 2020-06-12 Devavrat Shah , Dogyoon Song , Zhi Xu , Yuzhe Yang

Model-free reinforcement learning (RL) algorithms, such as Q-learning, directly parameterize and update value functions or policies without explicitly modeling the environment. They are typically simpler, more flexible to use, and thus more…

Machine Learning · Computer Science 2018-07-11 Chi Jin , Zeyuan Allen-Zhu , Sebastien Bubeck , Michael I. Jordan

Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space. To avoid the sampling variability, class imbalance, and data-privacy concerns…

Machine Learning · Computer Science 2021-10-26 Korawat Tanwisuth , Xinjie Fan , Huangjie Zheng , Shujian Zhang , Hao Zhang , Bo Chen , Mingyuan Zhou

Improving sample efficiency is central to Reinforcement Learning (RL), especially in environments where the rewards are sparse. Some recent approaches have proposed to specify reward functions as manually designed or learned reward…

Machine Learning · Computer Science 2024-01-26 Shuai Han , Mehdi Dastani , Shihan Wang

Social and real-world considerations such as robustness, fairness, social welfare and multi-agent tradeoffs have given rise to multi-distribution learning paradigms, such as collaborative learning, group distributionally robust…

Machine Learning · Computer Science 2024-04-04 Nika Haghtalab , Michael I. Jordan , Eric Zhao

In complex environments with high dimension, training a reinforcement learning (RL) model from scratch often suffers from lengthy and tedious collection of agent-environment interactions. Instead, leveraging expert demonstration to guide RL…

Machine Learning · Computer Science 2021-09-28 Zhaorun Chen , Binhao Chen , Shenghan Xie , Liang Gong , Chengliang Liu , Zhengfeng Zhang , Junping Zhang