Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Suhail M. Shah"'
Publikováno v:
IEEE Internet of Things Journal. 10:7993-8013
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b7985bf63e5d2cc25e1cd00084aea31
https://doi.org/10.1109/jiot.2022.3230452
https://doi.org/10.1109/jiot.2022.3230452
Publikováno v:
IEEE Transactions on Control of Network Systems
IEEE Transactions on Control of Network Systems, 2022, 9 (3), pp.1435-1446. ⟨10.1109/TCNS.2021.3114377⟩
IEEE Transactions on Control of Network Systems, IEEE, 2021, ⟨10.1109/TCNS.2021.3114377⟩
IEEE Transactions on Control of Network Systems, 2022, 9 (3), pp.1435-1446. ⟨10.1109/TCNS.2021.3114377⟩
IEEE Transactions on Control of Network Systems, IEEE, 2021, ⟨10.1109/TCNS.2021.3114377⟩
International audience; We introduce a model of graph-constrained dynamic choice with reinforcement modeled by positively $\alpha$-homogeneous rewards. We show that its empirical process, which can be written as a stochastic approximation recursion w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b12c430d9ea1b5f9dc499bfed0533f1c
https://doi.org/10.1109/tcns.2021.3114377
https://doi.org/10.1109/tcns.2021.3114377
Autor:
Suhail M. Shah, Vivek S. Borkar
Publikováno v:
Systems & Control Letters. 113:45-51
A reinforcement learning algorithm is proposed in order to solve a multi-criterion Markov decision process, i.e., an MDP with a vector running cost. Specifically, it combines a Q-learning scheme for a weighted linear combination of the prescribed run
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::05e9dca1fb2427b890b87927e96f62a2
https://doi.org/10.1016/j.sysconle.2018.01.003
https://doi.org/10.1016/j.sysconle.2018.01.003
Autor:
Suhail M. Shah, Vivek S. Borkar
Publikováno v:
SIAM Journal on Optimization. 28:3375-3401
We propose a distributed version of a stochastic approximation scheme constrained to remain in the intersection of a finite family of convex sets. The projection to the intersection of these sets is also computed in a distributed manner and a `nonlin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1506f4a466e778ff710cd3422a5d8de8
https://doi.org/10.1137/17m1128460
https://doi.org/10.1137/17m1128460
Autor:
Suhail M. Shah
The standard theory of stochastic approximation (SA) is extended to the case when the constraint set is a Riemannian manifold. Specifically, the standard ODE method for analyzing SA schemes is extended to iterations constrained to stay on a manifold
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::42597be4f703c1c3aeb00ad446acc57d
http://arxiv.org/abs/1711.10754
http://arxiv.org/abs/1711.10754
Autor:
Suhail M. Shah, Vivek S. Borkar
Publikováno v:
Advances in Dynamic and Mean Field Games ISBN: 9783319706184
We consider a controlled stochastic dynamics on a connected graph with gossip-like nearest neighbor affine interactions on a faster time scale. In the limit as the time scale separation diverges, followed by a limit as the graph grows to an infinite
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7ff0789130fe80812c6846f47693a5e4
https://doi.org/10.1007/978-3-319-70619-1_6
https://doi.org/10.1007/978-3-319-70619-1_6