Probabilistic Constraint for Safety-Critical Reinforcement Learning

arXiv:2306.17279v2 Announce Type: replace
Abstract: In this paper, we consider the problem of learning safe policies for probabilistic-constrained reinforcement learning (RL). Specifically, a safe policy or controller is one that, with high probability, maintains the trajectory of the agent in a given safe set. We establish a connection between this probabilistic-constrained setting and the cumulative-constrained formulation that is frequently explored in the existing literature. We provide theoretical bounds elucidating that the probabilistic-constrained setting offers a better trade-off in terms of …

abstract agent arxiv cs.ai cs.lg paper policy probability reinforcement reinforcement learning safety safety-critical set trajectory type