Synthesizing Safe Policies under Probabilistic Constraints with Reinforcement Learning and Bayesian Model Checking release_627eymbrxzbbjal7ag4drhgh4e

by Lenz Belzner, Martin Wirsing

Released as a article .

2020  

Abstract

In this paper we propose Policy Synthesis under probabilistic Constraints (PSyCo), a systematic engineering method for synthesizing safe policies under probabilistic constraints with reinforcement learning and Bayesian model checking. As an implementation of PSyCo we introduce Safe Neural Evolutionary Strategies (SNES). SNES leverages Bayesian model checking while learning to adjust the Lagrangian of a constrained optimization problem derived from a PSyCo specification. We empirically evaluate SNES' ability to synthesize feasible policies in settings with formal safety requirements.
In text/plain format

Archived Files and Locations

application/pdf  1.0 MB
file_neuth4uqfzgqxa2p7uqakbyeha
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-05-08
Version   v1
Language   en ?
arXiv  2005.03898v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: a7947d6e-74c6-431d-970a-0574281c977c
API URL: JSON