1 code implementation • 26 Jan 2023 • Prashant Trivedi, Nandyala Hemachandra
The proof requires the convergence of cost function parameters, the MAEVI algorithm, and analysis of the regret bounds induced by the MAEVI triggering condition for each agent.
no code implementations • 3 Sep 2021 • Prashant Trivedi, Nandyala Hemachandra
We observe an almost 25\% reduction in the average congestion in 2 MAN algorithms; the average congestion in another MAN algorithm is on par with the MAAC algorithm.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 12 Jan 2020 • Sandhya Tripathi, N. Hemachandra, Prashant Trivedi
For feature selection and related problems, we introduce the notion of classification game, a cooperative game, with features as players and hinge loss based characteristic function and relate a feature's contribution to Shapley value based error apportioning (SVEA) of total training error.