Click here to flash read.
We raise concerns about controllers' robustness in simple reinforcement
learning benchmark problems. We focus on neural network controllers and their
low neuron and symbolic abstractions. A typical controller reaching high mean
return values still generates an abundance of persistent low-return solutions,
which is a highly undesirable property, easily exploitable by an adversary. We
find that the simpler controllers admit more persistent bad solutions. We
provide an algorithm for a systematic robustness study and prove existence of
persistent solutions and, in some cases, periodic orbits, using a
computer-assisted proof methodology.
Click here to read this post out
ID: 301693; Unique Viewers: 0
Voters: 0
Latest Change: July 31, 2023, 7:31 a.m.
Changes:
Dictionaries:
Words:
Spaces:
Comments:
Newcom