Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Thinh T. Doan"'
Publikováno v:
IEEE Transactions on Automatic Control. 68:3273-3284
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::096e92fdf9759cf6bc84afcff314dc18
https://doi.org/10.1109/tac.2022.3190032
https://doi.org/10.1109/tac.2022.3190032
Autor:
Thinh T. Doan
Publikováno v:
IEEE Transactions on Automatic Control. 68:2140-2153
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9332a45b694a548b3c4c82901cce35c0
https://doi.org/10.1109/tac.2022.3172593
https://doi.org/10.1109/tac.2022.3172593
Publikováno v:
2022 IEEE 61st Conference on Decision and Control (CDC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::39639c65dc7ad4457c204056ce06a51e
https://doi.org/10.1109/cdc51059.2022.9993200
https://doi.org/10.1109/cdc51059.2022.9993200
Publikováno v:
2022 IEEE 61st Conference on Decision and Control (CDC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7683c15ab6ec86d5c7ca8952ee061843
https://doi.org/10.1109/cdc51059.2022.9992900
https://doi.org/10.1109/cdc51059.2022.9992900
Publikováno v:
IEEE Transactions on Automatic Control. 66:4469-4484
We study gradient methods for solving distributed convex optimization problems over a network when the communication bandwidth between the nodes is limited, and so information that is exchanged between the nodes must be quantized. This imperfect comm
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::babdeda0bf6fe551d4daf695305c97ad
https://doi.org/10.1109/tac.2020.3031018
https://doi.org/10.1109/tac.2020.3031018
Publikováno v:
SIAM Journal on Mathematics of Data Science. 3:298-320
We study the policy evaluation problem in multi-agent reinforcement learning, modeled by a Markov decision process. In this problem, the agents operate in a common environment under a fixed control...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b6f2d244fb8e18c96e0024ee6dcb789d
https://doi.org/10.1137/20m1311971
https://doi.org/10.1137/20m1311971
Publikováno v:
IEEE Transactions on Wireless Communications. :1-1
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::01e986804fd1977b580b1df0c33e6f0c
https://doi.org/10.1109/twc.2022.3233436
https://doi.org/10.1109/twc.2022.3233436
Autor:
Thinh T. Doan
Publikováno v:
2021 Seventh Indian Control Conference (ICC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4418d0f12a4c028a248b6dbd307b611a
https://doi.org/10.1109/icc54714.2021.9703179
https://doi.org/10.1109/icc54714.2021.9703179
Publikováno v:
2021 60th IEEE Conference on Decision and Control (CDC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b7015b556d3140884d98bdf1e54033e4
https://doi.org/10.1109/cdc45484.2021.9683363
https://doi.org/10.1109/cdc45484.2021.9683363
Given a collection of parameterized multi-robot controllers associated with individual behaviors designed for particular tasks, this paper considers the problem of how to sequence and instantiate the behaviors for the purpose of completing a more com
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::207bfa16118e0d02354c71db39830822
https://hdl.handle.net/10919/111712
https://hdl.handle.net/10919/111712
