Testing AI Learning in Open-World Novelty Scenarios (TALONS)

reportActive / Technical Report | Accesssion Number: AD1206086 | Open PDF

Abstract:

This report transmits the results of the Option period of the Phase II continuance of the TALONS SBIR. PacMar Technologies (PMT) and Parallax Advanced Research extended the development of a set of domain independent theories, principled techniques, and software tools for generating, characterizing, and evaluating novelty. These theories and techniques covering novelties are domain independent. The agent evaluation software tool developed under this SBIR is described in this report as well. The framework developed to support the self-driving car domain (CARLA) in the base period was extended to be compatible with the Monopoly domain, Vizdoom domain, and a PMT maritime domain. Efforts under this report were to support the DARPA SAIL-ON program.

Author(s):
Grinnell, Bryan ; Bercasio, Mark ; Wong, Allison ; Dannenhauer, Dustin ; Molineaux, Matthew
Author Organization(s):
PacMar Technologies LLC
Funding Organization(s):
DEFENSE ADVANCED RESEARCH PROJECTS AGENCY ARLINGTON VA, ARLINGTON, VA
Document Type:
SBIR Report/Final Report
Publication Date:
2023 Jul 14
Pagination:
312

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution Code:
A - Approved For Public Release
Distribution Statement: Public Release.
Copyright: Not Copyrighted

RECORD

Collection: TRECMS
Identifying Numbers
Contract Number(s):
HR001121C0236
 Subject Terms
Descriptor(s):
platforms
Keyword(s):
SAIL-ON(Science of Artificial Intelligence and Learning for Open-world Novelty), Novelty, V and V, CARLA, AI, T-SAL, TSAL, PMT, TALONS, PMT, PACMAR, PacMAR Technologies, Parallax, novelty generator, open world environments
Subject Categories:
Mathematical and Computer Sciences; Mathematical and Computer Sciences
Creation Date:
2023 Jul 20
Update Date:
2024 Apr 11