Safe Reinforcement Learning with Chance-constrained Model Predictive Control release_g2ciosj57zhprkgkpvxboj55jq

by Samuel Pfrommer, Tanmay Gautam, Alec Zhou, Somayeh Sojoudi

Released as a article .

2021  

Abstract

Real-world reinforcement learning (RL) problems often demand that agents behave safely by obeying a set of designed constraints. We address the challenge of safe RL by coupling a safety guide based on model predictive control (MPC) with a modified policy gradient framework in a linear setting with continuous actions. The guide enforces safe operation of the system by embedding safety requirements as chance constraints in the MPC formulation. The policy gradient training step then includes a safety penalty which trains the base policy to behave safely. We show theoretically that this penalty allows for the safety guide to be removed after training and illustrate our method using experiments with a simulator quadrotor.
In text/plain format

Archived Content

There are no accessible files associated with this release. You could check other releases for this work for an accessible version.

"Dark" Preservation Only
Save Paper Now!

Know of a fulltext copy of on the public web? Submit a URL and we will archive it

Type  article
Stage   submitted
Date   2021-12-27
Version   v1
Language   en ?
arXiv  2112.13941v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 3e71b0d2-e9ac-4a0e-b704-0f1a05a6d5d7
API URL: JSON