Physics-informed RL for Maximal Safety Probability Estimation

arXiv:2403.16391v1 Announce Type: cross
Abstract: Accurate risk quantification and reachability analysis are crucial for safe control and learning, but sampling from rare events, risky states, or long-term trajectories can be prohibitively costly. Motivated by this, we study how to estimate the long-term safety probability of maximally safe actions without sufficient coverage of samples from risky states and long-term trajectories. The use of maximal safety probability in control and learning is expected to avoid conservative behaviors due to over-approximation of risk. …

abstract analysis arxiv control coverage cs.lg cs.sy eess.sy events long-term physics physics-informed probability quantification risk safety samples sampling study type