English
Related papers

Related papers: Stabilizing Q-learning with Linear Architectures f…

200 papers

In the Economic Nonlinear Model Predictive (ENMPC) context, closed-loop stability relates to the existence of a storage function satisfying a dissipation inequality. Finding the storage function is in general -- for nonlinear dynamics and…

Systems and Control · Electrical Eng. & Systems 2021-10-26 Arash Bahari Kordabad , Sebastien Gros

The performance of a reinforcement learning (RL) system depends on the computational architecture used to approximate a value function. Deep learning methods provide both optimization techniques and architectures for approximating nonlinear…

Machine Learning · Computer Science 2021-06-21 John D. Martin , Joseph Modayil

Humans can naturally learn new and varying tasks in a sequential manner. Continual learning is a class of learning algorithms that updates its learned model as it sees new data (on potentially new tasks) in a sequence. A key challenge in…

Machine Learning · Computer Science 2025-03-04 Masih Eskandar , Tooba Imtiaz , Davin Hill , Zifeng Wang , Jennifer Dy

In many real world applications, reinforcement learning agents have to optimize multiple objectives while following certain rules or satisfying a list of constraints. Classical methods based on reward shaping, i.e. a weighted combination of…

Machine Learning · Computer Science 2020-09-15 Gabriel Kalweit , Maria Huegle , Moritz Werling , Joschka Boedecker

Stability is a basic requirement when studying the behavior of dynamical systems. However, stabilizing dynamical systems via reinforcement learning is challenging because only little data can be collected over short time horizons before…

Optimization and Control · Mathematics 2024-11-01 Steffen W. R. Werner , Benjamin Peherstorfer

As a primary contribution, we present a convergence theorem for stochastic iterations, and in particular, Q-learning iterates, under a general, possibly non-Markovian, stochastic environment. Our conditions for convergence involve an…

Optimization and Control · Mathematics 2024-03-05 Ali Devran Kara , Serdar Yuksel

Many practical reinforcement learning environments have a discrete factored action space that induces a large combinatorial set of actions, thereby posing significant challenges. Existing approaches leverage the regular structure of the…

Machine Learning · Computer Science 2025-05-01 Junkyu Lee , Tian Gao , Elliot Nelson , Miao Liu , Debarun Bhattacharjya , Songtao Lu

Deep Reinforcement Learning (RL) methods rely on experience replay to approximate the minibatched supervised learning setting; however, unlike supervised learning where access to lots of training data is crucial to generalization,…

Machine Learning · Computer Science 2021-02-24 Brett Daley , Cameron Hickert , Christopher Amato

Reinforcement learning algorithms are commonly analyzed (and designed) under the Markov assumption. This is unrealistic, as most environments encountered in practice are either partially observable, or require function approximation that…

Machine Learning · Computer Science 2026-05-28 Onno Eberhard , Claire Vernade , Michael Muehlebach

For a general standardized testing algorithm designed to evaluate a specific aspect of a robot's performance, several key expectations are commonly imposed. Beyond accuracy (i.e., closeness to a typically unknown ground-truth reference) and…

Robotics · Computer Science 2025-12-22 Bowen Weng , Linda Capito , Guillermo A. Castillo , Dylan Khor

Recursive Neural Networks are non-linear adaptive models that are able to learn deep structured information. However, these models have not yet been broadly accepted. This fact is mainly due to its inherent complexity. In particular, not…

Neural and Evolutionary Computing · Computer Science 2009-11-18 Alejandro Chinea

Continual Learning trains models on a stream of data, with the aim of learning new information without forgetting previous knowledge. Given the dynamic nature of such environments, explaining the predictions of these models can be…

Machine Learning · Computer Science 2023-06-21 Andrea Cossu , Francesco Spinnato , Riccardo Guidotti , Davide Bacciu

Adversarial training is a standard defense against malicious input perturbations in security-critical machine-learning systems. Its main burden is structural: before every parameter update, the current model must first be attacked to find a…

Quantum Physics · Physics 2026-03-31 Yue Wang , Guangyi He , Liepeng Zhang , Lukas Gonon , Qi Zhao

In this work, a new class of stochastic gradient algorithm is developed based on $q$-calculus. Unlike the existing $q$-LMS algorithm, the proposed approach fully utilizes the concept of $q$-calculus by incorporating time-varying $q$…

Optimization and Control · Mathematics 2018-01-03 Shujaat Khan , Alishba Sadiq , Imran Naseem , Roberto Togneri , Mohammed Bennamoun

The exploration-exploitation dilemma has been a central challenge in reinforcement learning (RL) with complex model classes. In this paper, we propose a new algorithm, Monotonic Q-Learning with Upper Confidence Bound (MQL-UCB) for RL with…

Machine Learning · Computer Science 2025-10-06 Heyang Zhao , Jiafan He , Quanquan Gu

Inspired by Double Q-learning algorithm, the Double-DQN (DDQN) algorithm was originally proposed in order to address the overestimation issue in the original DQN algorithm. The DDQN has successfully shown both theoretically and empirically…

Artificial Intelligence · Computer Science 2024-10-30 Shervin Halat , Mohammad Mehdi Ebadzadeh , Kiana Amani

Stability is a central property in learning and statistics promising the output of an algorithm $A$ does not change substantially when applied to similar datasets $S$ and $S'$. It is an elementary fact that any sufficiently stable algorithm…

Machine Learning · Computer Science 2025-02-13 Max Hopkins , Shay Moran

Most reinforcement learning algorithms take advantage of an experience replay buffer to repeatedly train on samples the agent has observed in the past. Not all samples carry the same amount of significance and simply assigning equal…

Machine Learning · Computer Science 2023-11-02 Shivakanth Sujit , Somjit Nath , Pedro H. M. Braga , Samira Ebrahimi Kahou

This paper considers the stability of online learning algorithms and its implications for learnability (bounded regret). We introduce a novel quantity called {\em forward regret} that intuitively measures how good an online learning…

Machine Learning · Computer Science 2012-11-28 Ankan Saha , Prateek Jain , Ambuj Tewari

Although parameter-efficient fine-tuning methods, such as LoRA, only modify a small subset of parameters, they can have a significant impact on the model. Our instruction-tuning experiments show that LoRA-based supervised fine-tuning can…

Machine Learning · Computer Science 2025-12-30 Matthew Riemer , Erik Miehling , Miao Liu , Djallel Bouneffouf , Murray Campbell