Predict-and-Critic: Accelerated End-to-End Predictive Control for Cloud Computing through Reinforcement Learning

no code implementations • 2 Dec 2022 • Kaustubh Sridhar, Vikramank Singh, Balakrishnan Narayanaswamy, Abishek Sankararaman

PnC jointly trains a prediction model and a terminal Q function that approximates cost-to-go over a long horizon, by back-propagating the cost of decisions through the optimization problem \emph{and from the future}.

Cloud Computing Model Predictive Control

PDQN - A Deep Reinforcement Learning Method for Planning with Long Delays: Optimization of Manufacturing Dispatching

no code implementations • 29 Sep 2021 • David C Jenkins, René Arendt Sørensen, Vikramank Singh, Philip Kaminsky, Anil Aswani, Ramakrishna Akella

This paper proposes a novel method based on Deep Reinforcement Learning for developing dynamic scheduling policies through interaction with simulated stochastic manufacturing systems.

Decision Making reinforcement-learning +2