Výsledky vyhledávání - "Anderson R. Tavares"

Multi-Objective, Multi-Armed Bandits: Algorithms for Repeated Games and Application to Route Choice

Autor: Candy A. Huanca-Anquise, Ana Lúcia Cetertich Bazzan, Anderson R. Tavares

Publikováno v: Revista de Informática Teórica e Aplicada; Vol. 30 No. 1 (2023); 11-23
Revista de Informática Teórica e Aplicada; v. 30 n. 1 (2023); 11-23

Multi-objective decision-making in multi-agent scenarios poses multiple challenges. Dealing with multiple objectives and non-stationarity caused by simultaneous learning are only two of them, which have been addressed separately. In this work, reinfo

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f2c97e12284524a6cb5c8373982e097f
https://doi.org/10.22456/2175-2745.122929

Zobrazit plný text záznamu

Algorithm Selection in Adversarial Settings: From Experiments to Tournaments in StarCraft

Autor: Anderson R. Tavares, Luiz Chaimowicz, Daniel K. S. Vieira, Tiago Negrisoli

Publikováno v: IEEE Transactions on Games. 11:238-247

Algorithm selection—the mapping of problem instances to algorithms—has been successfully applied to a variety of complex theoretical and practical problems, including computer games. In this paper, we extend the traditional framework, which consi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::31f64e221af4189ea1c0659fe844599d
https://doi.org/10.1109/tg.2018.2880147

Zobrazit plný text záznamu

Discrete and Continuous Deep Residual Learning over Graphs

Autor: Luis C. Lamb, Anderson R. Tavares, Marco Gori, Pedro H. C. Avelar

Publikováno v: ICAART (2)

In this paper we propose the use of continuous residual modules for graph kernels in Graph Neural Networks. We show how both discrete and continuous residual layers allow for more robust training, being that continuous residual layers are those which

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c77ef46e8d17d798aab645540e7b5b3
https://doi.org/10.5220/0010231501190131

Zobrazit plný text záznamu

EPGAT: Gene Essentiality Prediction With Graph Attention Networks

Autor: Mariana Recamonde-Mendoza, Anderson R. Tavares, Joao Schapke

The identification of essential genes/proteins is a critical step towards a better understanding of human biology and pathology. Computational approaches helped to mitigate experimental constraints by exploring machine learning (ML) methods and the c

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5df0a60ca265abce5f44955a431b3e67

Zobrazit plný text záznamu

Superpixel Image Classification with Graph Attention Networks

Autor: Claudio Rosito Jung, Anderson R. Tavares, Pedro H. C. Avelar, Thiago L. T. da Silveira, Luis C. Lamb

Publikováno v: SIBGRAPI

This paper presents a methodology for image classification using Graph Neural Network (GNN) models. We transform the input images into region adjacency graphs (RAGs), in which regions are superpixels and edges connect neighboring superpixels. Our exp

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::baeb4202a03bb8c2246fe59c6d60c799

Zobrazit plný text záznamu

Tabular Reinforcement Learning in Real-Time Strategy Games via Options

Autor: Anderson R. Tavares, Luiz Chaimowicz

Publikováno v: CIG

Real-Time Strategy (RTS) games are complex domains with huge state and action spaces. In such games, humans usually pursue long-term plans, which take long sequences of actions to achieve. In this work, we implement this behavior by reasoning over op

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::920bcfb14f28d17bb86ca93d28e789f8
https://doi.org/10.1109/cig.2018.8490427

Zobrazit plný text záznamu

Algorithms or Actions? A Study in Large-Scale Reinforcement Learning

Autor: Anderson R. Tavares, Luiz Chaimowicz, Leandro Soriano Marcolino, Sivasubramanian Anbalagan

Publikováno v: IJCAI

Large state and action spaces are very challenging to reinforcement learning. However, in many domains there is a set of algorithms available, which estimate the best action given a state. Hence, agents can either directly learn a performance-maximiz

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::91ad3b3b6fec03bfe8c888c372cc8c2e
https://doi.org/10.24963/ijcai.2018/377

Zobrazit plný text záznamu

Combining genetic algorithm and swarm intelligence for task allocation in a real time strategy game

Autor: Hector Azpurua, Anderson R. Tavares, Luiz Chaimowicz, Gianlucca Zuin

Publikováno v: Journal on Interactive Systems. 8:1

Real time strategy games are complex scenarios where multiple agents must be coordinated in a dynamic, partially observable environment. In this work, we model coordination as a task allocation problem, in which specific tasks must be properly assign

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::aeb89a78ba21eefcfea5c7e01bf743a1
https://doi.org/10.5753/jis.2017.671

Zobrazit plný text záznamu

Evolving Swarm Intelligence for Task Allocation in a Real Time Strategy Game

Autor: Hector Azpurua, Anderson R. Tavares, Luiz Chaimowicz

Publikováno v: SBGames

Real time strategy games are complex scenarioswhere multiple agents must be coordinated in a dynamic,partially observable environment. In this work, we model thecoordination of these agents as a task allocation problem, in which specific tasks are gi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::cc4ebd87b10f0eb9c819b6215e3992db
https://doi.org/10.1109/sbgames.2014.17

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání