Zobrazeno 1 - 10
of 69
pro vyhledávání: '"Vakili, Sattar"'
Autor:
Vakili, Sattar, Olkhovskaya, Julia
Reinforcement learning utilizing kernel ridge regression to predict the expected value function represents a powerful method with great representational capacity. This setting is a highly versatile framework amenable to analytical results. We conside
Externí odkaz:
http://arxiv.org/abs/2410.23498
Autor:
Vakili, Sattar
Reinforcement Learning (RL) has shown great empirical success in various application domains. The theoretical aspects of the problem have been extensively studied over past decades, particularly under tabular and linear Markov Decision Process struct
Externí odkaz:
http://arxiv.org/abs/2406.15250
Autor:
Shidani, Amitis, Vakili, Sattar
We consider regret minimization in a general collaborative multi-agent multi-armed bandit model, in which each agent faces a finite set of arms and may communicate with other agents through a central controller. The optimal arm for each agent in this
Externí odkaz:
http://arxiv.org/abs/2312.09674
We study the robust best-arm identification problem (RBAI) in the case of linear rewards. The primary objective is to identify a near-optimal robust arm, which involves selecting arms at every round and assessing their robustness by exploring potenti
Externí odkaz:
http://arxiv.org/abs/2311.04731
We consider Bayesian optimization using Gaussian Process models, also referred to as kernel-based bandit optimization. We study the methodology of exploring the domain using random samples drawn from a distribution. We show that this random explorati
Externí odkaz:
http://arxiv.org/abs/2310.15351
We study a generalization of the problem of online learning in adversarial linear contextual bandits by incorporating loss functions that belong to a reproducing kernel Hilbert space, which allows for a more flexible modeling of complex decision-maki
Externí odkaz:
http://arxiv.org/abs/2310.01609
Channel modelling is essential to designing modern wireless communication systems. The increasing complexity of channel modelling and the cost of collecting high-quality wireless channel data have become major challenges. In this paper, we propose a
Externí odkaz:
http://arxiv.org/abs/2308.05583
Autor:
Vakili, Sattar, Olkhovskaya, Julia
Reinforcement learning (RL) has shown empirical success in various real world settings with complex models and large state-action spaces. The existing analytical results, however, typically focus on settings with a small number of state-actions or si
Externí odkaz:
http://arxiv.org/abs/2306.07745
Autor:
Das, Ayan, Fotiadis, Stathi, Batra, Anil, Nabiei, Farhang, Liao, FengTing, Vakili, Sattar, Shiu, Da-shan, Bernacchia, Alberto
The field of image generation has made significant progress thanks to the introduction of Diffusion Models, which learn to progressively reverse a given image corruption. Recently, a few studies introduced alternative ways of corrupting images in Dif
Externí odkaz:
http://arxiv.org/abs/2306.00501
Autor:
Picheny, Victor, Berkeley, Joel, Moss, Henry B., Stojic, Hrvoje, Granta, Uri, Ober, Sebastian W., Artemev, Artem, Ghani, Khurram, Goodall, Alexander, Paleyes, Andrei, Vakili, Sattar, Pascual-Diaz, Sergio, Markou, Stratis, Qing, Jixiang, Loka, Nasrulloh R. B. S, Couckuyt, Ivo
We present Trieste, an open-source Python package for Bayesian optimization and active learning benefiting from the scalability and efficiency of TensorFlow. Our library enables the plug-and-play of popular TensorFlow-based models within sequential d
Externí odkaz:
http://arxiv.org/abs/2302.08436