A simple formalism Artificial intelligence-based to represent knowledge in a multi-agent planning context
Journal Title: International Journal of Information Technology and Applied Sciences (IJITAS) - Year 2020, Vol 2, Issue 1
Abstract
At the start of the simulation, the agent knows nothing about how the dynamics of interaction with the environment unfold, or what causes his sensations. He does not distinguish obstacles from free paths, and he does not know the consequences implied by his actions. Under these conditions, the CALM mechanism was able to converge steadily towards the expected solution, by building a model of the world adequate to represent the regularities of the environment, the regularities of its bodily sensations, as well as to represent the influence regular actions on both. The agent learns about the consequences of his actions in different situations, which are represented by a reduced number of very general diagrams. From them, the mechanism can build an action policy that allows it to avoid affectively negative situations and to seek those that are affectively positive. This solution manages to describe precisely all the regularities that the agent can perceive without building a complete plan of the environment.
Authors and Affiliations
Imane Ben
Keywords
Related Articles
- EP ID EP694263
- DOI https://doi.org/10.52502/ijitas.v2i1.7
- Views 212
- Downloads 0
Object detection and object classification using machine learning Algorithms
Urban objects are characterized by a very variable representation in terms of shape, texture and color. In addition, they are present multiple times on the images to be analyzed and can be stuck to each other. To carry o...
Machine Learning confronted with the operational constraints of detection systems
Intrusion detection systems, traditionally based on signatures, have not escaped the recent appeal of machine learning techniques. While the results presented in academic research articles are often excellent, security e...
Localized Farmer’s Information Dissemination System in Nigeria Using Mobile Networks
Agricultural science performs a substantial function in monetary and societal growth in nearly all developing nations. Data on satisfactory excellence is an indispensable criterion for the development of all fields of fa...
A simple formalism Artificial intelligence-based to represent knowledge in a multi-agent planning context
At the start of the simulation, the agent knows nothing about how the dynamics of interaction with the environment unfold, or what causes his sensations. He does not distinguish obstacles from free paths, and he does not...
A new MPPT technique for optimal and efficient monitoring in case of environmental or load conditions variation
Due to the very high initial investment cost of photovoltaic systems and their low conversion efficiency, it is essential to operate PV generators at the point of maximum power (MPP). Within this framework, our first obj...