Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Arunselvan Ramaswamy"'
Publikováno v:
IEEE Access, Vol 12, Pp 70707-70718 (2024)
This paper introduces SATS, an innovative online task scheduling strategy tailored for hierarchical Mobile Edge Computing (MEC) architectures. Leveraging a Simulated Annealing-based approach, SATS extends the applicability of this method beyond offli
Externí odkaz:
https://doaj.org/article/9f50254f83074d18b355f109e2411a7d
Publikováno v:
Mathematics of Operations Research. 47:2138-2159
In this paper, we consider the stochastic iterative counterpart of the value iteration scheme wherein only noisy and possibly biased approximations of the Bellman operator are available. We call this counterpart the approximate value iteration (AVI)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::17e73047748b4ead1e00b7ed6ce5b054
https://doi.org/10.1287/moor.2021.1202
https://doi.org/10.1287/moor.2021.1202
Publikováno v:
IEEE Transactions on Automatic Control. 67:4131-4137
Solving optimization problems in multi-agent systems typically involves information exchange between agents using wireless networks with evolving topologies. The obtained solutions should be robust to possibly unbounded information delays and errors
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::741d0c380381032d47af8ab725163198
https://doi.org/10.1109/tac.2021.3108492
https://doi.org/10.1109/tac.2021.3108492
Autor:
Arunselvan Ramaswamy, Eyke Hüllermeier
Publikováno v:
IEEE Transactions on Artificial Intelligence. 3:139-151
Deep Q-Learning is an important reinforcement learning algorithm, which involves training a deep neural network, called Deep Q-Network (DQN), to approximate the well-known Q-function. Although wildly successful under laboratory conditions, serious ga
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c90458a14d0357c6e0be8e117496d805
https://doi.org/10.1109/tai.2021.3111142
https://doi.org/10.1109/tai.2021.3111142
Autor:
Arunselvan Ramaswamy
Publikováno v:
Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ce5728aaae00f6f96a93c960f8866bf6
https://doi.org/10.5220/0011678000003411
https://doi.org/10.5220/0011678000003411
Publikováno v:
2022 58th Annual Allerton Conference on Communication, Control, and Computing (Allerton).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::38ff8602b5425b59906ae55245187628
https://doi.org/10.1109/allerton49937.2022.9929396
https://doi.org/10.1109/allerton49937.2022.9929396
Publikováno v:
Pervasive and Mobile Computing. 92:101799
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4eee8982ead75b101b43516a0996f7cd
https://doi.org/10.1016/j.pmcj.2023.101799
https://doi.org/10.1016/j.pmcj.2023.101799
Autor:
Pritha Gupta, Arunselvan Ramaswamy, Jan Drees, Eyke Hüllermeier, Claudia Priesterjahn, Tibor Jager
Publikováno v:
Proceedings of the 14th International Conference on Agents and Artificial Intelligence.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e4ecdf0ea227632344ea9766417327ae
https://doi.org/10.5220/0010793000003116
https://doi.org/10.5220/0010793000003116
The decentralized nature of multi-Agent learning often requires continuous information exchange over a (wireless) communication network, in order to accomplish common global objectives. Uncertainty and delay in communication induce large Age of Infor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::adb99fff78f274b84071f5ffe6f5cf7a
http://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-91986
http://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-91986
Publikováno v:
Proceedings of the 14th International Conference on Agents and Artificial Intelligence.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b27edc4c0844c0002495ef18d5515fe0
https://doi.org/10.5220/0010845400003116
https://doi.org/10.5220/0010845400003116