Multi-Constraint Safe RL with Objective Suppression for Safety-Critical Applications
Zhou, Zihan, Booher, Jonathan, Rohanimanesh, Khashayar, Liu, Wei, Petiushko, Aleksandr, Garg, Animesh
–arXiv.org Artificial Intelligence
Safe reinforcement learning tasks with multiple constraints are a challenging domain despite being very common in the real world. In safety-critical domains, properly handling the constraints becomes even more important. To address this challenge, we first describe the multi-constraint problem with a stronger Uniformly Constrained MDP (UCMDP) model; we then propose Objective Suppression, a novel method that adaptively suppresses the task reward maximizing objectives according to a safety critic, as a solution to the Lagrangian dual of a UCMDP. We benchmark Objective Suppression in two multi-constraint safety domains, including an autonomous driving domain where any incorrect behavior can lead to disastrous consequences. Empirically, we demonstrate that our proposed method, when combined with existing safe RL algorithms, can match the task reward achieved by our baselines with significantly fewer constraint violations.
arXiv.org Artificial Intelligence
Apr-15-2024
- Country:
- North America
- Canada > Ontario
- Toronto (0.14)
- United States (0.14)
- Canada > Ontario
- North America
- Genre:
- Research Report (0.84)
- Technology: