Safe Reinforcement Learning with Learned Non-Markovian Safety Constraints

arXiv:2405.03005v1 Announce Type: new
Abstract: In safe Reinforcement Learning (RL), safety cost is typically defined as a function dependent on the immediate state and actions. In practice, safety constraints can often be non-Markovian due to the insufficient fidelity of state representation, and safety cost may not be known. We therefore address a general setting where safety labels (e.g., safe or unsafe) are associated with state-action trajectories. Our key contributions are: first, we design a safety model that specifically performs credit …

abstract arxiv constraints cost cs.ai cs.lg fidelity function practice reinforcement reinforcement learning representation safe safety state type