Zobrazeno 1 - 10
of 53 743
pro vyhledávání: '"A Yüksel"'
We develop rigorous approximation and near optimality results for the optimal control of a system which is connected to a controller over a finite rate noiseless channel. While structural results on the optimal encoding and control have been obtained
Externí odkaz:
http://arxiv.org/abs/2411.13884
Autor:
Yüksel, Yusuf
We have performed Monte Carlo simulations for the investigation of dynamic phase transitions on a honeycomb lattice which has garnered a significant amount of interest from the viewpoint of tailoring the intrinsic magnetism in two-dimensional materia
Externí odkaz:
http://arxiv.org/abs/2411.13119
The paper studies the robustness properties of discrete-time stochastic optimal control under Wasserstein model approximation for both discounted cost and average cost criteria. Specifically, we study the performance loss when applying an optimal pol
Externí odkaz:
http://arxiv.org/abs/2410.14116
Constrained Reinforcement Learning (CRL) is a subset of machine learning that introduces constraints into the traditional reinforcement learning (RL) framework. Unlike conventional RL which aims solely to maximize cumulative rewards, CRL incorporates
Externí odkaz:
http://arxiv.org/abs/2410.08022
This paper addresses the problem of long-context linear system identification, where the state $x_t$ of a dynamical system at time $t$ depends linearly on previous states $x_s$ over a fixed context window of length $p$. We establish a sample complexi
Externí odkaz:
http://arxiv.org/abs/2410.05690
Finding optimal policies for Partially Observable Markov Decision Processes (POMDPs) is challenging due to their uncountable state spaces when transformed into fully observable Markov Decision Processes (MDPs) using belief states. Traditional methods
Externí odkaz:
http://arxiv.org/abs/2409.04351
Autor:
Mrani-Zentar, Omar, Yüksel, Serdar
Decentralized stochastic control problems are intrinsically difficult to study because of the inapplicability of standard tools from centralized control such as dynamic programming and the resulting computational complexity. In this paper, we address
Externí odkaz:
http://arxiv.org/abs/2408.13828
Multiple choice question answering tasks evaluate the reasoning, comprehension, and mathematical abilities of Large Language Models (LLMs). While existing benchmarks employ automatic translation for multilingual evaluation, this approach is error-pro
Externí odkaz:
http://arxiv.org/abs/2407.12402
Autor:
Luo, Haocong, Yüksel, Ismail Emir, Olgun, Ataberk, Yağlıkçı, A. Giray, Sadrosadati, Mohammad, Mutlu, Onur
DRAM read disturbance can break memory isolation, a fundamental property to ensure system robustness (i.e., reliability, security, safety). RowHammer and RowPress are two different DRAM read disturbance phenomena. RowHammer induces bitflips in physic
Externí odkaz:
http://arxiv.org/abs/2406.13080
Autor:
Selk, Zachary, Yüksel, Serdar
Decentralized stochastic control problems with local information involve problems where multiple agents and subsystems which are coupled via dynamics and/or cost are present. Typically, however, the dynamics of such couplings is complex and difficult
Externí odkaz:
http://arxiv.org/abs/2405.20498