Advantage of prediction and mental imagery for goal‐directed behaviour in agents and robots. Issue 1 (4th February 2019)

• Record Type: Journal Article
• Authors: Krichmar, Jeffrey L.; Hwu, Tiffany; Zou, Xinyun; Hylton, Todd
• Is Part Of: Cognitive computation and systems. Volume 1:Issue 1(2019)
• Page Start: 12
• Page End: 19
• Publication Date: 2019-02-04
• Subjects: cognitive systems -- cognition -- artificial intelligence -- brain -- predator‐prey systems; energy budget -- food intake -- physical robots -- cognitive behaviour -- mental simulation -- environmental fitness -- thermodynamically driven theories -- brain function -- predator–prey scenario -- mental imagery -- agent goal‐directed behaviour -- actor critic agents -- forward planning agents -- artificial cognitive systems; Cognitive science -- Periodicals; Artificial intelligence -- Periodicals; Neurosciences -- Periodicals; Computer science -- Periodicals; Neurosciences; Computer science; Cognitive science; Artificial intelligence; Periodicals; Electronic journals; 006.3
• DOI: 10.1049/ccs.2018.0002
• Languages: English
• ISSNs: 2517-7567

Abstract

Abstract : Mental imagery and planning are important aspects of cognitive behaviour. Being able to predict outcomes through mental simulation can increase environmental fitness and reduce uncertainty. Such predictions reduce surprise and fit with thermodynamically driven theories of brain function by attempting to reduce entropy. In the present work, the authors tested these ideas in a predator–prey scenario where agents with a limited energy budget had to maximise food intake, while avoiding a predator. Forward planning agents, with the ability to mentalise, to Actor Critic agents that do not plan beyond the current state were also compared. The authors show that the ability to mentalise has distinct advantages when in noisy, uncertain stimuli. These advantages are even more prevalent when tested in the real world on physical robots. The authors' results highlight the importance of taking into consideration mental imagery and embodiment when constructing artificial cognitive systems.