An Adiabatic Theorem for Policy Tracking with TD-learning
From MaRDI portal
Abstract: We evaluate the ability of temporal difference learning to track the reward function of a policy as it changes over time. Our results apply a new adiabatic theorem that bounds the mixing time of time-inhomogeneous Markov chains. We derive finite-time bounds for tabular temporal difference learning and -learning when the policy used for training changes in time. To achieve this, we develop bounds for stochastic approximation under asynchronous adiabatic updates.
This page was built for publication: An Adiabatic Theorem for Policy Tracking with TD-learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6352137)
