TY - JOUR
T1 - A Neurosymbolic Cognitive Architecture Framework for Handling Novelties in Open Worlds
AU - Goel, Shivam
AU - Lymperopoulos, Panagiotis
AU - Thielstrom, Ravenna
AU - Krause, Evan
AU - Feeney, Patrick
AU - Lorang, Pierrick
AU - Schneider, Sarah Anna
AU - Wei, Yichen
AU - Kildebeck, Eric
AU - Goss, Stephen
AU - Hughes, Michael C.
AU - Liu, Liping
AU - Sinapov, Jivko
AU - Scheutz, Matthias
PY - 2024/6
Y1 - 2024/6
N2 - “Open world” environments are those in which novel objects, agents, events, and more can appear and contradict previous understandings of the environment. This contradicts the “closed world” assumption used in most AI research, where the environment is assumed to be fully understood and unchanging. The types of environments AI agents can be deployed in are limited by the inability to handle the novelties that occur in open world environments. This paper presents a novel cognitive architecture framework to handle open-world novelties. This framework combines symbolic planning, counterfactual reasoning, reinforcement learning, and deep computer vision to detect and accommodate novelties. We introduce general algorithms for exploring open worlds using inference and machine learning methodologies to facilitate novelty accommodation. The ability to detect and accommodate novelties allows agents built on this framework to successfully complete tasks despite a variety of novel changes to the world. Both the framework components and the entire system are evaluated in Minecraft-like simulated environments. Our results indicate that agents are able to efficiently complete tasks while accommodating “concealed novelties” not shared with the architecture development team.
AB - “Open world” environments are those in which novel objects, agents, events, and more can appear and contradict previous understandings of the environment. This contradicts the “closed world” assumption used in most AI research, where the environment is assumed to be fully understood and unchanging. The types of environments AI agents can be deployed in are limited by the inability to handle the novelties that occur in open world environments. This paper presents a novel cognitive architecture framework to handle open-world novelties. This framework combines symbolic planning, counterfactual reasoning, reinforcement learning, and deep computer vision to detect and accommodate novelties. We introduce general algorithms for exploring open worlds using inference and machine learning methodologies to facilitate novelty accommodation. The ability to detect and accommodate novelties allows agents built on this framework to successfully complete tasks despite a variety of novel changes to the world. Both the framework components and the entire system are evaluated in Minecraft-like simulated environments. Our results indicate that agents are able to efficiently complete tasks while accommodating “concealed novelties” not shared with the architecture development team.
KW - open-world novelty
KW - cognitive architecture
KW - learning and perception
KW - creative problem solving
UR - https://www.mendeley.com/catalogue/0b397d37-a78a-3326-adf0-d43a86577ee3/
U2 - 10.1016/j.artint.2024.104111
DO - 10.1016/j.artint.2024.104111
M3 - Article
SN - 0004-3702
VL - 331
JO - Artificial Intelligence
JF - Artificial Intelligence
M1 - 104111
ER -