Pith. sign in

REVIEW

Robust Regression for Safe Exploration in Control

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1906.05819 v2 pith:J2TNXVXU submitted 2019-06-13 cs.LG cs.SYeess.SYstat.ML

classification cs.LGcs.SYeess.SYstat.ML
keywords controlexplorationsafeboundsregressionrobustuncertaintychallenge
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We study the problem of safe learning and exploration in sequential control problems. The goal is to safely collect data samples from operating in an environment, in order to learn to achieve a challenging control goal (e.g., an agile maneuver close to a boundary). A central challenge in this setting is how to quantify uncertainty in order to choose provably-safe actions that allow us to collect informative data and reduce uncertainty, thereby achieving both improved controller safety and optimality. To address this challenge, we present a deep robust regression model that is trained to directly predict the uncertainty bounds for safe exploration. We derive generalization bounds for learning, and connect them with safety and stability bounds in control. We demonstrate empirically that our robust regression approach can outperform the conventional Gaussian process (GP) based safe exploration in settings where it is difficult to specify a good GP prior.

Discussion (0). Sign in to comment.

Pith tools