Format

Send to

Choose Destination
IEEE Trans Neural Netw Learn Syst. 2017 Nov.;28(11):2528-2540. doi: 10.1109/TNNLS.2016.2596787.

Needs, Pains, and Motivations in Autonomous Agents.

Author information

1
Russ College of Electrical Engineering and Computer Science, Ohio University, Athens, OH, USA.
2
School of Computer Science and Management, University of Information Technology and Management, Rzeszów, Poland.

Abstract

This paper presents the development of a motivated learning (ML) agent with symbolic I/O. Our earlier work on the ML agent was enhanced, giving it autonomy for interaction with other agents. Specifically, we equipped the agent with drives and pains that establish its motivations to learn how to respond to desired and undesired events and create related abstract goals. The purpose of this paper is to explore the autonomous development of motivations and memory in agents within a simulated environment. The ML agent has been implemented in a virtual environment created within the NeoAxis game engine. Additionally, to illustrate the benefits of an ML-based agent, we compared the performance of our algorithm against various reinforcement learning (RL) algorithms in a dynamic test scenario, and demonstrated that our ML agent learns better than any of the tested RL agents.This paper presents the development of a motivated learning (ML) agent with symbolic I/O. Our earlier work on the ML agent was enhanced, giving it autonomy for interaction with other agents. Specifically, we equipped the agent with drives and pains that establish its motivations to learn how to respond to desired and undesired events and create related abstract goals. The purpose of this paper is to explore the autonomous development of motivations and memory in agents within a simulated environment. The ML agent has been implemented in a virtual environment created within the NeoAxis game engine. Additionally, to illustrate the benefits of an ML-based agent, we compared the performance of our algorithm against various reinforcement learning (RL) algorithms in a dynamic test scenario, and demonstrated that our ML agent learns better than any of the tested RL agents.

KEYWORDS:

Cognition; Computer architecture; Computer science; Heuristic algorithms; Learning systems; Pain; Robots

PMID:
27542184
DOI:
10.1109/TNNLS.2016.2596787

Supplemental Content

Full text links

Icon for IEEE Engineering in Medicine and Biology Society
Loading ...
Support Center