(the set of interaction possibilities they have with the world),Īnd the execution engine at their disposal Like biological systems, these agents program themselves using the instruction set at their disposal We draw inspiration from natural cognitive systems to design self-programming agents. The only thing at its disposal that remotely resembles an execution engine is its cognitive system which allows it to execute and learn sequences of interactions with the world. The only thing at its disposal that remotely resembles an instruction set is the set of interaction possibilities it has with the world around it. To understand the full implication of this definition, it is important to take a cognitive science perspective rather than a software development perspective.Ī natural cognitive system (an animal) does not have a compiler or an interpreter to exploit a programming language. Self-programming agents also run a predefined program, but this program can control the execution of learned data as sequences of instructions. Traditional machine learning agents, however, run a predefined program that exploits this data as parameters. Similar to other machine learning agents, self-programming agents record data in memory as they learn. ![]() ![]() We define a self-programming agent as an agent that can autonomously acquire executable code Introduction Introduction to self-programming Defining self-programming Implementation of DEvelopmentAl Learning (IDEAL) CourseĤ1.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |