Guaranteeing Control Requirements via Reward Shaping in Reinforcement Learning

arXiv:2311.10026v2 Announce Type: replace-cross
Abstract: In addressing control problems such as regulation and tracking through reinforcement learning, it is often required to guarantee that the acquired policy meets essential performance and stability criteria such as a desired settling time and steady-state error prior to deployment. Motivated by this necessity, we present a set of results and a systematic reward shaping procedure that (i) ensures the optimal policy generates trajectories that align with specified control requirements and (ii) allows to assess …

abstract acquired arxiv control cs.lg cs.sy deployment eess.sy error performance policy prior regulation reinforcement reinforcement learning requirements stability state through tracking type via