English
Related papers

Related papers: A Geometric Nash Approach in Tuning the Learning R…

200 papers

We obtain essentially tight upper bounds for a strengthened notion of regret in the stochastic linear bandits framework. The strengthening -- referred to as Nash regret -- is defined as the difference between the (a priori unknown) optimum…

Machine Learning · Computer Science 2023-10-04 Ayush Sawarni , Soumybrata Pal , Siddharth Barman

Variational Quantum Algorithms (VQAs) employ parameterized quantum circuits optimized using classical methods to minimize a cost function. While VQAs have found broad applications, certain challenges persist. Notably, a significant…

Quantum Physics · Physics 2025-03-06 Lucas Friedrich , Jonas Maziero

The Q-learning algorithm is known to be affected by the maximization bias, i.e. the systematic overestimation of action values, an important issue that has recently received renewed attention. Double Q-learning has been proposed as an…

Machine Learning · Computer Science 2021-02-03 Rong Zhu , Mattia Rigotti

This paper studies an intriguing phenomenon related to the good generalization performance of estimators obtained by using large learning rates within gradient descent algorithms. First observed in the deep learning literature, we show that…

Machine Learning · Statistics 2022-06-06 Gaspard Beugnot , Julien Mairal , Alessandro Rudi

This work examines a stochastic formulation of the generalized Nash equilibrium problem (GNEP) where agents are subject to randomness in the environment of unknown statistical distribution. We focus on fully-distributed online learning by…

Computer Science and Game Theory · Computer Science 2017-06-28 Chung-Kai Yu , Mihaela van der Schaar , Ali H. Sayed

This work proposes a novel distributed approach for computing a Nash equilibrium in convex games with restricted strongly monotone pseudo-gradients. By leveraging the idea of the centralized operator extrapolation method presented in [4] to…

Optimization and Control · Mathematics 2023-10-25 Tatiana Tatarenko , Angelia Nedich

Off-policy, value-based reinforcement learning methods such as Q-learning are appealing because they can learn from arbitrary experience, including data collected by older policies or other agents. In practice, however, bootstrapping makes…

Artificial Intelligence · Computer Science 2026-05-12 Armaan A. Abraham , Lucy Xiaoyang Shi , Chelsea Finn

We study the global convergence of generative adversarial imitation learning for linear quadratic regulators, which is posed as minimax optimization. To address the challenges arising from non-convex-concave geometry, we analyze the…

Machine Learning · Computer Science 2019-01-15 Qi Cai , Mingyi Hong , Yongxin Chen , Zhaoran Wang

We study the problem of learning-to-learn: inferring a learning algorithm that works well on tasks sampled from an unknown distribution. As class of algorithms we consider Stochastic Gradient Descent on the true risk regularized by the…

Machine Learning · Computer Science 2019-03-26 Giulia Denevi , Carlo Ciliberto , Riccardo Grazzi , Massimiliano Pontil

We consider learning Nash equilibria in two-player zero-sum Markov Games with nonlinear function approximation, where the action-value function is approximated by a function in a Reproducing Kernel Hilbert Space (RKHS). The key challenge is…

Machine Learning · Computer Science 2022-08-11 Chris Junchi Li , Dongruo Zhou , Quanquan Gu , Michael I. Jordan

Robustness against adversarial attacks and distribution shifts is a long-standing goal of Reinforcement Learning (RL). To this end, Robust Adversarial Reinforcement Learning (RARL) trains a protagonist against destabilizing forces exercised…

Machine Learning · Computer Science 2023-11-06 Aryaman Reddi , Maximilian Tölle , Jan Peters , Georgia Chalvatzaki , Carlo D'Eramo

The $Q$-learning algorithm is a simple and widely-used stochastic approximation scheme for reinforcement learning, but the basic protocol can exhibit instability in conjunction with function approximation. Such instability can be observed…

Machine Learning · Computer Science 2022-06-03 Andrea Zanette , Martin J. Wainwright

While Bayesian-based exploration often demonstrates superior empirical performance compared to bonus-based methods in model-based reinforcement learning (RL), its theoretical understanding remains limited for model-free settings. Existing…

Machine Learning · Computer Science 2026-02-05 He Wang , Xingyu Xu , Yuejie Chi

Existing convergence analyses of Q-learning mostly focus on the vanilla stochastic gradient descent (SGD) type of updates. Despite the Adaptive Moment Estimation (Adam) has been commonly used for practical Q-learning algorithms, there has…

Optimization and Control · Mathematics 2020-07-16 Bowen Weng , Huaqing Xiong , Yingbin Liang , Wei Zhang

Catastrophic forgetting is a critical challenge in training deep neural networks. Although continual learning has been investigated as a countermeasure to the problem, it often suffers from the requirements of additional network components…

Machine Learning · Computer Science 2019-10-23 Dongmin Park , Seokil Hong , Bohyung Han , Kyoung Mu Lee

This paper considers the problem of inverse reinforcement learning in zero-sum stochastic games when expert demonstrations are known to be not optimal. Compared to previous works that decouple agents in the game by assuming optimality in…

Machine Learning · Statistics 2018-06-07 Xingyu Wang , Diego Klabjan

Robots find extensive applications in industry. In recent years, the influence of robots has also increased rapidly in domestic scenarios. The Q-learning algorithm aims to maximise the reward for reaching the goal. This paper proposes a…

Robotics · Computer Science 2024-09-04 Varun Prakash Rajamohan , Senthil Kumar Jagatheesaperumal

Recent state-of-the-art methods for neural architecture search (NAS) exploit gradient-based optimization by relaxing the problem into continuous optimization over architectures and shared-weights, a noisy process that remains poorly…

Machine Learning · Computer Science 2021-03-19 Liam Li , Mikhail Khodak , Maria-Florina Balcan , Ameet Talwalkar

Dynamic games can be an effective approach to modeling interactive behavior between multiple non-cooperative agents and they provide a theoretical framework for simultaneous prediction and control in such scenarios. In this work, we propose…

Systems and Control · Electrical Eng. & Systems 2022-09-19 Edward L. Zhu , Francesco Borrelli

Neural architecture search has attracted wide attentions in both academia and industry. To accelerate it, researchers proposed weight-sharing methods which first train a super-network to reuse computation among different operators, from…

Machine Learning · Computer Science 2020-12-16 Xin Chen , Lingxi Xie , Jun Wu , Longhui Wei , Yuhui Xu , Qi Tian