Efficient adaptive allocation of resources for container-based computation via markov decision processes

Abstract

Systems and methods that enable the efficient and adaptive allocation of resources dedicated to a container-based computation (e.g., one or more information processing tasks) are provided. A container controller is employed to launch and dynamically update (e.g., manage) the resource allocation (e.g., indicated by a selected configuration) for a set of containers. The container controller implements a Markov Decision Process (MDP)-based control loop to adaptively configure (e.g., allocate resources for) and reconfigure the set of containers. In some embodiments, the MDP of the control loop is a single-state MDP (e.g., a multi-armed bandit decision process). In such embodiments, each possible configuration for the set of containers is an arm on the multi-armed bandit.