Zobrazeno 1 - 10
of 508
pro vyhledávání: '"A. Ramki"'
A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world, however, a
Externí odkaz:
http://arxiv.org/abs/2407.12185
Autor:
Che, Fengdi, Xiao, Chenjun, Mei, Jincheng, Dai, Bo, Gummadi, Ramki, Ramirez, Oscar A, Harris, Christopher K, Mahmood, A. Rupam, Schuurmans, Dale
Publikováno v:
Proceedings of the 41 st International Conference on Machine Learning, 2024
We prove that the combination of a target network and over-parameterized linear function approximation establishes a weaker convergence condition for bootstrapped value estimation in certain cases, even with off-policy data. Our condition is naturall
Externí odkaz:
http://arxiv.org/abs/2405.21043
Publikováno v:
Heliyon, Vol 10, Iss 13, Pp e33612- (2024)
Silicon oxycarbide (SiOC) exhibits good retention and a reasonable specific capacity and is an alternative to silicon used as an anode material for high-performance lithium-ion batteries. However, SiOC generally shows a low Initial Coulombic Efficien
Externí odkaz:
https://doaj.org/article/318532aac8c4457d8db11bd73facf664
Publikováno v:
ICML 2022
Approaches to policy optimization have been motivated from diverse principles, based on how the parametric model is interpreted (e.g. value versus policy representation) or how the learning objective is formulated, yet they share a common goal of max
Externí odkaz:
http://arxiv.org/abs/2206.08499
Autor:
Chellakannu, Arunbalaji, Karuppathevan, Ramki, Muniasamy, Kottaisamy, Sivasamy, Vasantha Vairathevar
Publikováno v:
In Journal of Molecular Structure 15 October 2024 1314
Publikováno v:
In Journal of Molecular Structure 15 January 2025 1320
Publikováno v:
In Heliyon 15 July 2024 10(13)
Actor-critic (AC) methods are ubiquitous in reinforcement learning. Although it is understood that AC methods are closely related to policy gradient (PG), their precise connection has not been fully characterized previously. In this paper, we explain
Externí odkaz:
http://arxiv.org/abs/2106.06932
Autor:
Karthik, Palani, Jose, Paulraj Adwin, Chellakannu, Arunbalaji, Gurusamy, Shunmugasundaram, Ananthappan, Periyasamy, Karuppathevan, Ramki, Vasantha, Vairathevar Sivasamy, Rajesh, Jegathalaprathaban, Ravichandran, Siranjeevi, Sankarganesh, Murugesan
Publikováno v:
In International Journal of Biological Macromolecules February 2024 258 Part 2
Publikováno v:
In Methods January 2024 221:1-11