English
Related papers

Related papers: Lipschitzness Is All You Need To Tame Off-policy G…

200 papers

We study unconstrained Online Linear Optimization with Lipschitz losses. Motivated by the pursuit of instance optimality, we propose a new algorithm that simultaneously achieves ($i$) the AdaGrad-style second order gradient adaptivity; and…

Machine Learning · Computer Science 2024-02-23 Zhiyu Zhang , Heng Yang , Ashok Cutkosky , Ioannis Ch. Paschalidis

Reinforcement Learning (RL) agents often struggle with inefficient exploration, particularly in environments with sparse rewards. Traditional exploration strategies can lead to slow learning and suboptimal performance because agents fail to…

Machine Learning · Computer Science 2026-03-31 Gaurav Chaudhary , Laxmidhar Behera , Washim Uddin Mondal

One of the challenges in the study of Generative Adversarial Networks (GANs) is the difficulty of its performance control. Lipschitz constraint is essential in guaranteeing training stability for GANs. Although heuristic methods such as…

Computer Vision and Pattern Recognition · Computer Science 2020-12-24 Kanglin Liu , Guoping Qiu

Recently, robust reinforcement learning (RL) methods designed to handle adversarial input observations have received significant attention, motivated by RL's inherent vulnerabilities. While existing approaches have demonstrated reasonable…

Machine Learning · Computer Science 2025-06-23 Kosuke Nakanishi , Akihiro Kubo , Yuji Yasui , Shin Ishii

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates are performed on data collected by older policies. This…

Machine Learning · Computer Science 2026-05-28 Otmane Sakhi , Aleksei Arzhantsev , Imad Aouali , Flavian Vasile

Interactive-Grounded Learning (IGL) [Xie et al., 2021] is a powerful framework in which a learner aims at maximizing unobservable rewards through interacting with an environment and observing reward-dependent feedback on the taken actions.…

Machine Learning · Computer Science 2024-06-03 Mengxiao Zhang , Yuheng Zhang , Haipeng Luo , Paul Mineiro

Imitation learning has proven effective for training robots to perform complex tasks from expert human demonstrations. However, it remains limited by its reliance on high-quality, task-specific data, restricting adaptability to the diverse…

Conditional Generative Adversarial Networks are known to be difficult to train, especially when the conditions are continuous and high-dimensional. To partially alleviate this difficulty, we propose a simple generator regularization term on…

Machine Learning · Computer Science 2021-03-30 Yufeng Zheng , Yunkai Zhang , Zeyu Zheng

Despite the significant potential for various applications, stochastic games with long-run average payoffs have received limited scholarly attention, particularly concerning the development of learning algorithms for them due to the…

Computer Science and Game Theory · Computer Science 2024-05-17 Junyue Zhang , Yifen Mu

We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions, i.e. environments more general than (PO)MDPs. The task for an agent is to attain…

Machine Learning · Computer Science 2009-12-30 Daniil Ryabko , Marcus Hutter

Many existing imitation learning datasets are collected from multiple demonstrators, each with different expertise at different parts of the environment. Yet, standard imitation learning algorithms typically treat all demonstrators as…

Machine Learning · Computer Science 2022-06-14 Mark Beliaev , Andy Shih , Stefano Ermon , Dorsa Sadigh , Ramtin Pedarsani

We study offline reinforcement learning in average-reward MDPs, which presents increased challenges from the perspectives of distribution shift and non-uniform coverage, and has been relatively underexamined from a theoretical perspective.…

Machine Learning · Computer Science 2026-04-23 Matthew Zurek , Guy Zamir , Yudong Chen

In this work, we take a fresh look at some old and new algorithms for off-policy, return-based reinforcement learning. Expressing these in a common form, we derive a novel algorithm, Retrace($\lambda$), with three desired properties: (1) it…

Machine Learning · Computer Science 2016-11-09 Rémi Munos , Tom Stepleton , Anna Harutyunyan , Marc G. Bellemare

Imitation learning can reproduce policies by observing experts, which poses a problem regarding policy privacy. Policies, such as human, or policies on deployed robots, can all be cloned without consent from the owners. How can we protect…

Machine Learning · Computer Science 2020-08-04 Albert Zhan , Stas Tiomkin , Pieter Abbeel

In this paper, an off-policy reinforcement learning algorithm is designed to solve the continuous-time LQR problem using only input-state data measured from the system. Different from other algorithms in the literature, we propose the use…

Systems and Control · Electrical Eng. & Systems 2023-04-03 Victor G. Lopez , Matthias A. Müller

Sample efficiency is crucial for imitation learning methods to be applicable in real-world applications. Many studies improve sample efficiency by extending adversarial imitation to be off-policy regardless of the fact that these off-policy…

Machine Learning · Computer Science 2022-04-14 Mingfei Sun , Sam Devlin , Katja Hofmann , Shimon Whiteson

We study reinforcement learning with linear function approximation and adversarially changing cost functions, a setup that has mostly been considered under simplifying assumptions such as full information feedback or exploratory…

Machine Learning · Computer Science 2023-01-31 Uri Sherman , Tomer Koren , Yishay Mansour

This paper presents a study of robust policy networks in deep reinforcement learning. We investigate the benefits of policy parameterizations that naturally satisfy constraints on their Lipschitz bound, analyzing their empirical performance…

Machine Learning · Computer Science 2025-02-07 Nicholas H. Barbara , Ruigang Wang , Ian R. Manchester

The construction by Du et al. (2019) implies that even if a learner is given linear features in $\mathbb R^d$ that approximate the rewards in a bandit with a uniform error of $\epsilon$, then searching for an action that is optimal up to…

Machine Learning · Statistics 2020-02-20 Tor Lattimore , Csaba Szepesvari , Gellert Weisz

We consider the contextual bandit problem on general action and context spaces, where the learner's rewards depend on their selected actions and an observable context. This generalizes the standard multi-armed bandit to the case where side…

Machine Learning · Statistics 2023-01-03 Moise Blanchard , Steve Hanneke , Patrick Jaillet
‹ Prev 1 3 4 5 6 7 10 Next ›