Verifiably Safe Exploration for End-to-End Reinforcement Learning

July 02, 2020 Β· Declared Dead Β· πŸ› International Conference on Hybrid Systems: Computation and Control

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Nathan Hunt, Nathan Fulton, Sara Magliacane, Nghia Hoang, Subhro Das, Armando Solar-Lezama arXiv ID 2007.01223 Category cs.AI: Artificial Intelligence Cross-listed cs.LG, cs.LO Citations 59 Venue International Conference on Hybrid Systems: Computation and Control Last Checked 4 months ago
Abstract
Deploying deep reinforcement learning in safety-critical settings requires developing algorithms that obey hard constraints during exploration. This paper contributes a first approach toward enforcing formal safety constraints on end-to-end policies with visual inputs. Our approach draws on recent advances in object detection and automated reasoning for hybrid dynamical systems. The approach is evaluated on a novel benchmark that emphasizes the challenge of safely exploring in the presence of hard constraints. Our benchmark draws from several proposed problem sets for safe learning and includes problems that emphasize challenges such as reward signals that are not aligned with safety constraints. On each of these benchmark problems, our algorithm completely avoids unsafe behavior while remaining competitive at optimizing for as much reward as is safe. We also prove that our method of enforcing the safety constraints preserves all safe policies from the original environment.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ‘» Ghosted