Advantage of prediction and mental imagery for goal‐directed behaviour in agents and robots
Uloženo v:
| Název: | Advantage of prediction and mental imagery for goal‐directed behaviour in agents and robots |
|---|---|
| Autoři: | Jeffrey L. Krichmar, Tiffany Hwu, Xinyun Zou, Todd Hylton |
| Zdroj: | Cognitive Computation and Systems (2019) |
| Informace o vydavateli: | Institution of Engineering and Technology (IET), 2019. |
| Rok vydání: | 2019 |
| Témata: | cognition, 0301 basic medicine, Computer engineering. Computer hardware, food intake, forward planning agents, brain, Computer applications to medicine. Medical informatics, R858-859.7, actor critic agents, mental simulation, brain function, TK7885-7895, 03 medical and health sciences, predator-prey systems, 0302 clinical medicine, agent goal-directed behaviour, cognitive behaviour, cognitive systems, environmental fitness, artificial cognitive systems, mental imagery, predator–prey scenario, artificial intelligence, physical robots, energy budget, thermodynamically driven theories |
| Popis: | 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. |
| Druh dokumentu: | Article Other literature type |
| Jazyk: | English |
| ISSN: | 2517-7567 |
| DOI: | 10.1049/ccs.2018.0002 |
| Přístupová URL adresa: | https://doaj.org/article/ede4830cc2ad42248aa1a5da2dded17d https://ieeexplore.ieee.org/document/8694213/ https://digital-library.theiet.org/content/journals/10.1049/ccs.2018.0002 https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/ccs.2018.0002 |
| Rights: | CC BY |
| Přístupové číslo: | edsair.doi.dedup.....07cf3de9a86eda10dbb0e18f0d7adcf6 |
| Databáze: | OpenAIRE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | 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. |
|---|---|
| ISSN: | 25177567 |
| DOI: | 10.1049/ccs.2018.0002 |