|
This article is cited in 3 scientific papers (total in 3 papers)
Intelligent control and behavior planning
Rational behaviour planning of cognitive semiotic agent in dynamic environment
G. S. Osipova, A. I. Panovab a Russian Artificial Intelligence Research Institute of the Russian Academy of Sciences, Moscow, Russia
b Moscow Institute of Physics and Technology (National Research University), Dolgoprudny, Moscow Region
Abstract:
The paper presents a general architecture of a cognitive semiotic agent acting in a dynamic environment. A new implementation and integration of the agent planning and learning subsystems are proposed to solve the symbol grounding problem. We suggest a new approach to the description of the semantic level of the sign-based world model component, which is used as a base for agent rational behavior synthesis. A formal definition of the behavior script and its use in generating a rational agent's action plan is proposed. In conclusion, we describe a model experiment that demonstrates the work of a semiotic agent in a game environment.
Keywords:
semiotic agent, sign-based world model, causal networks, semiotic network, planning, reinforcement learning.
Citation:
G. S. Osipov, A. I. Panov, “Rational behaviour planning of cognitive semiotic agent in dynamic environment”, Artificial Intelligence and Decision Making, 2020, no. 4, 80–100; Scientific and Technical Information Processing, 48:6 (2021), 502–516
Linking options:
https://www.mathnet.ru/eng/iipr154 https://www.mathnet.ru/eng/iipr/y2020/i4/p80
|
|