Degradation of Performance in Reinforcement Learning with State Measurement Uncertainty

Date

2019

Authors

McKenzie, M.
Mcdonnell, M.D.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

2019 Military Communications and Information Systems Conference, MilCIS 2019 - Proceedings, 2019, iss.8930725, pp.1-5

Statement of Responsibility

Conference Name

2019 Military Communications and Information Systems Conference (MilCIS) (12 Nov 2019 - 14 Nov 2019 : Canberra, ACT, Australia)

Abstract

We detail the use of open source training environments to investigate the applicability of standard reinforcement learning techniques to inherently error prone tasks expected in real world application of artificial intelligence. Numerical experiments were conducted in which the performance of both Q Learning and Policy Gradient agents' ability to obtain high reward was compared as the observation state measurement uncertainty was increased. The purpose of the research was to assess the applicability of reinforcement learning to real world applications of self-protection of military platforms, where it is expected that the observed state space is uncertain at best. We found in our experiments that Q Learning is more stable in the presence of state uncertainty than policy gradient learning.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

Copyright 2019 IEEE

License

Grant ID

Call number

Persistent link to this record