English
Related papers

Related papers: Sharp asymptotic theory for Q-learning with LDTZ l…

200 papers

Reinforcement Learning (RL) post-training has emerged as the dominant paradigm for eliciting mathematical reasoning in Large Language Models (LLMs), yet prevailing techniques such as GRPO and DAPO distribute rollout and gradient budgets…

Machine Learning · Computer Science 2026-05-20 Peng Cui , Boyao Yang , Jun Zhu

Modern Deep Reinforcement Learning (RL) algorithms require estimates of the maximal Q-value, which are difficult to compute in continuous domains with an infinite number of possible actions. In this work, we introduce a new update rule for…

Machine Learning · Computer Science 2023-03-02 Divyansh Garg , Joey Hejna , Matthieu Geist , Stefano Ermon

Current theoretical results on optimization trajectories of neural networks trained by gradient descent typically have the form of rigorous but potentially loose bounds on the loss values. In the present work we take a different approach…

Machine Learning · Computer Science 2021-05-04 Maksim Velikanov , Dmitry Yarotsky

The Zarantonello fixed-point iteration is an established linearization scheme for quasilinear PDEs with strongly monotone and Lipschitz continuous nonlinearity in Hilbert spaces. This paper presents a weighted least-squares minimization for…

Numerical Analysis · Mathematics 2026-02-24 Philipp Bringmann , Dirk Praetorius

We study model-free Q-learning in finite-horizon episodic Markov Decision Processes (MDPs) with stationary dynamics across episodes. We identify a central issue in nascent model-free posterior-sampling works: the reliance on delayed…

Machine Learning · Computer Science 2026-05-21 Sofia R. Miskala-Dinc , Aviva Prins

We present an efficient algorithm for model-free episodic reinforcement learning on large (potentially continuous) state-action spaces. Our algorithm is based on a novel $Q$-learning policy with adaptive data-driven discretization. The…

Machine Learning · Computer Science 2019-12-20 Sean R. Sinclair , Siddhartha Banerjee , Christina Lee Yu

A primary requirement for any reinforcement learning method is that it should produce policies that improve upon the initial guess. In this work, we show that the widely used Deep Q-Network (DQN) fails to satisfy this minimal criterion --…

Machine Learning · Computer Science 2025-06-18 Aditya Gopalan , Gugan Thoppe

In this paper, a novel Q-learning scheduling method for the current controller of switched reluctance motor (SRM) drive is investigated. Q-learning algorithm is a class of reinforcement learning approaches that can find the best…

Systems and Control · Electrical Eng. & Systems 2020-06-16 Hamad A. Alharkan , Sepehr Saadatmand , Mehdi Ferdowsi , Pourya Shamsi

When the data used for reinforcement learning (RL) are collected by multiple agents in a distributed manner, federated versions of RL algorithms allow collaborative learning without the need for agents to share their local data. In this…

Machine Learning · Computer Science 2023-12-14 Jiin Woo , Gauri Joshi , Yuejie Chi

While there are many advantages to deploying machine learning models on edge devices, the resource constraints of mobile platforms, the dynamic nature of the environment, and differences between the distribution of training versus…

Machine Learning · Computer Science 2025-03-21 Cynthia Dong , Hong Jia , Young D. Kwon , Georgios Rizos , Cecilia Mascolo

In his breakthrough paper, Raz showed that any parity learning algorithm requires either quadratic memory or an exponential number of samples [FOCS'16, JACM'19]. A line of work that followed extended this result to a large class of learning…

Machine Learning · Computer Science 2023-10-13 Xin Lyu , Avishay Tal , Hongxun Wu , Junzhao Yang

We give an efficient algorithm for learning a binary function in a given class C of bounded VC dimension, with training data distributed according to P and test data according to Q, where P and Q may be arbitrary distributions over X. This…

Machine Learning · Computer Science 2021-02-17 Adam Kalai , Varun Kanade

Training large models is both resource-intensive and time-consuming, making it crucial to understand the quantitative relationship between model performance and hyperparameters. In this paper, we present an empirical law that describes how…

Machine Learning · Computer Science 2025-03-18 Kairong Luo , Haodong Wen , Shengding Hu , Zhenbo Sun , Zhiyuan Liu , Maosong Sun , Kaifeng Lyu , Wenguang Chen

Reinforcement learning algorithms often require finiteness of state and action spaces in Markov decision processes (MDPs) (also called controlled Markov chains) and various efforts have been made in the literature towards the applicability…

Machine Learning · Computer Science 2023-09-08 Ali Devran Kara , Naci Saldi , Serdar Yüksel

Model-free approaches for reinforcement learning (RL) and continuous control find policies based only on past states and rewards, without fitting a model of the system dynamics. They are appealing as they are general purpose and easy to…

Machine Learning · Computer Science 2018-10-09 Yasin Abbasi-Yadkori , Nevena Lazic , Csaba Szepesvari

Q-learning has become an important part of the reinforcement learning toolkit since its introduction in the dissertation of Chris Watkins in the 1980s. The purpose of this paper is in part a tutorial on stochastic approximation and…

Machine Learning · Computer Science 2023-08-22 Sean Meyn

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

We give the first fully polynomial-time algorithm for learning halfspaces with respect to the uniform distribution on the hypercube in the presence of contamination, where an adversary may corrupt some fraction of examples and labels…

Data Structures and Algorithms · Computer Science 2025-11-11 Gautam Chandrasekaran , Adam R. Klivans , Konstantinos Stavropoulos , Arsen Vasilyan

Quantization is an effective technique to reduce memory footprint, inference latency, and power consumption of deep learning models. However, existing quantization methods suffer from accuracy degradation compared to full-precision (FP)…

Machine Learning · Computer Science 2022-10-14 Zheng Wang , Juncheng B Li , Shuhui Qu , Florian Metze , Emma Strubell

Complex learning rate schedules have become an integral part of deep learning. We find empirically that common fine-tuned schedules decay the learning rate after the weight norm bounces. This leads to the proposal of ABEL: an automatic…

Machine Learning · Computer Science 2021-03-24 Aitor Lewkowycz
‹ Prev 1 4 5 6 7 8 10 Next ›