Finding Partitions for Learning Control of Dynamic Systems

摘要

When a dynamic systems is controlled by a learning controller, the state space is required to be coarsely partitioned to make the learning task computationally feasible. This partition forms the representation of hte dynamic system to the learning algorithm. However, such representations normally make the system non-Markovian and thus ard to control, do not naturally allow for asymptotic approach of the setpoint, and often necessitate large control actions.