Verifiably Safe Off-Model Reinforcement Learning

02/14/2019
by   Nathan Fulton, et al.
0

The desire to use reinforcement learning in safety-critical settings has inspired a recent interest in formal methods for learning algorithms. Existing formal methods for learning and optimization primarily consider the problem of constrained learning or constrained optimization. Given a single correct model and associated safety constraint, these approaches guarantee efficient learning while provably avoiding behaviors outside the safety constraint. Acting well given an accurate environmental model is an important pre-requisite for safe learning, but is ultimately insufficient for systems that operate in complex heterogeneous environments. This paper introduces verification-preserving model updates, the first approach toward obtaining formal safety guarantees for reinforcement learning in settings where multiple environmental models must be taken into account. Through a combination of design-time model updates and runtime model falsification, we provide a first approach toward obtaining formal safety proofs for autonomous systems acting in heterogeneous environments.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/27/2019

Safe Reinforcement Learning on Autonomous Vehicles

There have been numerous advances in reinforcement learning, but the typ...
research
11/15/2021

Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning

Safety is the major consideration in controlling complex dynamical syste...
research
09/06/2021

Safe Reinforcement Learning using Formal Verification for Tissue Retraction in Autonomous Robotic-Assisted Surgery

Deep Reinforcement Learning (DRL) is a viable solution for automating re...
research
03/06/2023

Constrained Reinforcement Learning and Formal Verification for Safe Colonoscopy Navigation

The field of robotic Flexible Endoscopes (FEs) has progressed significan...
research
12/14/2020

Safe Reinforcement Learning with Stability Safety Guarantees Using Robust MPC

Reinforcement Learning offers tools to optimize policies based on the da...
research
02/24/2023

SEO: Safety-Aware Energy Optimization Framework for Multi-Sensor Neural Controllers at the Edge

Runtime energy management has become quintessential for multi-sensor aut...
research
06/30/2020

It's Time to Play Safe: Shield Synthesis for Timed Systems

Erroneous behaviour in safety critical real-time systems may inflict ser...

Please sign up or login with your details

Forgot password? Click here to reset