Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Mert Kayaalp"'
Publikováno v:
IEEE Open Journal of Control Systems, Vol 2, Pp 125-145 (2023)
Most works on multi-agent reinforcement learning focus on scenarios where the state of the environment is fully observable. In this work, we consider a cooperative policy evaluation task in which agents are not assumed to observe the environment stat
Externí odkaz:
https://doaj.org/article/9d55b1808f214fd182204a72d9333d37
Publikováno v:
IEEE Open Journal of Signal Processing, Vol 4, Pp 188-207 (2023)
The adaptive social learning paradigm helps model how networked agents are able to form opinions on a state of nature and track its drifts in a changing environment. In this framework, the agents repeatedly update their beliefs based on private obser
Externí odkaz:
https://doaj.org/article/4e7220c126554b4b831d83edc2354c7f
Publikováno v:
IEEE Open Journal of Signal Processing, Vol 3, Pp 71-93 (2022)
The objective of meta-learning is to exploit knowledge obtained from observed tasks to improve adaptation to unseen tasks. Meta-learners are able to generalize better when they are trained with a larger number of observed tasks and with a larger amou
Externí odkaz:
https://doaj.org/article/369f34958e574c3d8e21b71b875e00be
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::42a89975d1c439e10ae03916d4176ccf
https://doi.org/10.1109/icassp49357.2023.10094722
https://doi.org/10.1109/icassp49357.2023.10094722
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b704f537e33d38cc6588e3e50f6dd3ca
https://doi.org/10.1109/icassp49357.2023.10096238
https://doi.org/10.1109/icassp49357.2023.10096238
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0ffe8a40a667b7f05875d5c43e8852fa
https://doi.org/10.1109/icassp49357.2023.10097172
https://doi.org/10.1109/icassp49357.2023.10097172
This work proposes a multi-agent filtering algorithm over graphs for finite-state hidden Markov models (HMMs), which can be used for sequential state estimation or for tracking opinion formation over dynamic social networks. We show that the differen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::61ee58b3b010cd130fad2f1babd503da
http://arxiv.org/abs/2111.13626
http://arxiv.org/abs/2111.13626
Publikováno v:
2021 29th European Signal Processing Conference (EUSIPCO).
Meta-learning aims to improve efficiency of learning new tasks by exploiting the inductive biases obtained from related tasks. Previous works consider centralized or federated architectures that rely on central processors, whereas, in this paper, we
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d426210a409aaa0973ed89eeeae8267a
https://doi.org/10.23919/eusipco54536.2021.9616256
https://doi.org/10.23919/eusipco54536.2021.9616256
Publikováno v:
IEEE Open Journal of Signal Processing, Vol 3, Pp 71-93 (2022)
The objective of meta-learning is to exploit the knowledge obtained from observed tasks to improve adaptation to unseen tasks. As such, meta-learners are able to generalize better when they are trained with a larger number of observed tasks and with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::839d521fd327a3811ac7e38fd2ed03c9
http://arxiv.org/abs/2010.02870
http://arxiv.org/abs/2010.02870
The adaptive social learning paradigm helps model how networked agents are able to form opinions on a state of nature and track its drifts in a changing environment. In this framework, the agents repeatedly update their beliefs based on private obser
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e8c62dd8395c582595cddbdc4a99bc8
https://infoscience.epfl.ch/record/302281
https://infoscience.epfl.ch/record/302281