English
Related papers

Related papers: Diminishing Return of Value Expansion Methods

200 papers

Despite the numerous advances, reinforcement learning remains away from widespread acceptance for autonomous controller design as compared to classical methods due to lack of ability to effectively tackle the reality gap. The reliance on…

Machine Learning · Computer Science 2024-09-23 Narendra Patwardhan , Zequn Wang

We introduce the technique of adaptive discretization to design an efficient model-based episodic reinforcement learning algorithm in large (potentially continuous) state-action spaces. Our algorithm is based on optimistic one-step value…

Machine Learning · Computer Science 2020-10-26 Sean R. Sinclair , Tianyu Wang , Gauri Jain , Siddhartha Banerjee , Christina Lee Yu

Q-learning methods represent a commonly used class of algorithms in reinforcement learning: they are generally efficient and simple, and can be combined readily with function approximators for deep reinforcement learning (RL). However, the…

Machine Learning · Computer Science 2019-02-28 Justin Fu , Aviral Kumar , Matthew Soh , Sergey Levine

Learning-based control methods typically assume stationary system dynamics, an assumption often violated in real-world systems due to drift, wear, or changing operating conditions. We study reinforcement learning for control under…

Machine Learning · Computer Science 2026-04-03 Klemens Iten , Bruce Lee , Chenhao Li , Lenart Treven , Andreas Krause , Bhavya Sukhija

Reducing reinforcement learning to supervised learning is a well-studied and effective approach that leverages the benefits of compact function approximation to deal with large-scale Markov decision processes. Independently, the boosting…

Machine Learning · Computer Science 2023-01-26 Nataly Brukhim , Elad Hazan , Karan Singh

Model-free deep-reinforcement-based learning algorithms have been applied to a range of COPs~\cite{bello2016neural}~\cite{kool2018attention}~\cite{nazari2018reinforcement}. However, these approaches suffer from two key challenges when…

Machine Learning · Computer Science 2022-06-01 Nasrin Sultana , Jeffrey Chan , Tabinda Sarwar , A. K. Qin

Compounding error, where small prediction mistakes accumulate over time, presents a major challenge in learning-based control. For example, this issue often limits the performance of model-based reinforcement learning and imitation…

Systems and Control · Electrical Eng. & Systems 2025-04-03 Anne Somalwar , Bruce D. Lee , George J. Pappas , Nikolai Matni

Score-based diffusion models, while achieving minimax optimality for sampling, are often hampered by slow sampling speeds due to the high computational burden of score function evaluations. Despite the recent remarkable empirical advances…

Machine Learning · Computer Science 2025-02-27 Gen Li , Changxiao Cai

Deep reinforcement learning (RL) algorithms have recently achieved remarkable successes in various sequential decision making tasks, leveraging advances in methods for training large deep networks. However, these methods usually require…

Machine Learning · Computer Science 2020-06-30 Kei Ota , Tomoaki Oiki , Devesh K. Jha , Toshisada Mariyama , Daniel Nikovski

Policy gradient methods are very attractive in reinforcement learning due to their model-free nature and convergence guarantees. These methods, however, suffer from high variance in gradient estimation, resulting in poor sample efficiency.…

Machine Learning · Computer Science 2018-11-16 Sergey Pankov

Model-based Reinforcement Learning (MBRL) allows data-efficient learning which is required in real world applications such as robotics. However, despite the impressive data-efficiency, MBRL does not achieve the final performance of…

Machine Learning · Computer Science 2019-08-19 Zhang-Wei Hong , Joni Pajarinen , Jan Peters

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

The capability to widely sample the state and action spaces is a key ingredient toward building effective reinforcement learning algorithms. The variational optimization principles exposed in this paper emphasize the importance of an…

Machine Learning · Computer Science 2022-05-25 Emmanuel Daucé

Standard approaches for variable selection in linear models are not tailored to deal properly with high-dimensional and incomplete data. Currently, methods dedicated to high-dimensional data handle missing values by ad-hoc strategies, like…

Methodology · Statistics 2021-06-09 Avner Bar-Hen , Vincent Audigier

Model compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a…

Machine Learning · Computer Science 2021-09-28 Sebastian Cygert , Andrzej Czyżewski

Dynamic data selection aims to accelerate training with lossless performance. However, reducing training data inherently limits data diversity, potentially hindering generalization. While data augmentation is widely used to enhance…

Machine Learning · Computer Science 2025-05-13 Suorong Yang , Peng Ye , Furao Shen , Dongzhan Zhou

Several approaches have been proposed to improve the sample efficiency of online reinforcement learning (RL) by leveraging demonstrations collected offline. The offline data can be used directly as transitions to optimize RL objectives, or…

Robotics · Computer Science 2026-03-31 Dwait Bhatt , Shih-Chieh Chou , Nikolay Atanasov

Standard language models generate text by selecting tokens from a fixed, finite, and standalone vocabulary. We introduce a novel method that selects context-aware phrases from a collection of supporting documents. One of the most…

Computation and Language · Computer Science 2024-03-19 Bowen Cao , Deng Cai , Leyang Cui , Xuxin Cheng , Wei Bi , Yuexian Zou , Shuming Shi

In the presence of a missing response, reweighting the complete case subsample by the inverse of nonmissing probability is both intuitive and easy to implement. When the population totals of some auxiliary variables are known and when the…

Methodology · Statistics 2014-10-16 Kwun Chuen Gary Chan , Sheung Chi Phillip Yam

Two-phase outcome dependent sampling (ODS) is widely used in many fields, especially when certain covariates are expensive and/or difficult to measure. For two-phase ODS, the conditional maximum likelihood (CML) method is very attractive…

Methodology · Statistics 2022-12-21 Menglu Che , Peisong Han , Jerald F. Lawless