Restless Bandit Problem with Rewards Generated by a Linear Gaussian Dynamical System.

Jonathan Gornet Bruno Sinopoli

Published in: CoRR (2024)

Keyphrases

dynamical systems
bandit problems
linear gaussian
state space
nonlinear dynamical systems
dynamic systems
dynamical behavior
reinforcement learning
immune network
markov decision processes
optimal control
partially observable
bayesian networks
markov chain
random sampling
generative model
mobile robot