Toward Computational Motivation for Multi-Agent Systems and Swarms

  title={Toward Computational Motivation for Multi-Agent Systems and Swarms},
  author={Md Mohiuddin Khan and Kathryn Kasmarik and Michael Barlow},
  journal={Frontiers in Robotics and AI},
Motivation is a crucial part of animal and human mental development, fostering competence, autonomy, and open-ended development. Motivational constructs have proved to be an integral part of explaining human and animal behavior. Computer scientists have proposed various computational models of motivation for artificial agents, with the aim of building artificial agents capable of autonomous goal generation. Multi-agent systems and swarm intelligence are natural extensions to the individual… 

Figures and Tables from this paper

Foundations of Erobotics

It is argued that a new unified transdisciplinary field of research—grounded in sexuality and technology positive frameworks—focusing on human-erobot interaction and co-evolution as well as guiding the development of beneficial erotic machines is needed, called Erobotics.

Towards Ecosystem Management from Greedy Reinforcement Learning in a Predator-Prey Setting

Reinforcement learning is applied to train a predator to hunt multiple prey, which are able to reproduce, in a 2D simulation.



Cooperative Multi-Agent Learning: The State of the Art

This survey attempts to draw from multi-agent learning work in a spectrum of areas, including RL, evolutionary computation, game theory, complex systems, agent modeling, and robotics, and finds that this broad view leads to a division of the work into two categories.

Task allocation in multi-agent systems using models of motivation and leadership

The proposed approach uses the Particle Swarm Optimization algorithm with a ring neighborhood topology as a foundation and incorporates computational models of motivation to achieve the goals of task allocation more effectively.

Evolution and Learning in an Intrinsically Motivated Reinforcement Learning Robot

The most important results show that systems using both evolution and learning outperform systems using either one of the two, and that systems evolving internal reinforcers for learning building-block skills have a higher evolvability than those directly evolving the related behaviors.

Evolution of Collective Behaviors by Minimizing Surprisal and by Micro-Macro Links

Two opportunities are presented to leverage the robot-robot interactions to basically bootstrap the system and to trigger the emergence of complex behaviors and to leverage macroscopic swarm effects by making use of swarm models.

A Comprehensive Survey of Multiagent Reinforcement Learning

The benefits and challenges of MARL are described along with some of the problem domains where the MARL techniques have been applied, and an outlook for the field is provided.

Evolution of Intrinsic Motives in Multi-agent Simulations

This paper presents evolutionary models of intrinsically motivated agents that are evaluated in multi-agent simulations of agents playing iterated prisoner's dilemma games.

Novelty-Seeking Multi-Agent Systems

It is shown that novelty-seeking multi-agent systems can be more productive in generating novel artifacts than a single-agent or monolithic system.

Achievement, affiliation, and power: Motive profiles for artificial agents

Three new computational models of motivation for achievement, affiliation, and power motivation are presented, designed such that they can be used in isolation or together, embedded in an artificial ‘‘motive profile’’.

Intrinsically Motivated Learning in Natural and Artificial Systems

This book introduces the concept of intrinsic motivation in artificial systems, reviews the relevant literature, offers insights from the neural and behavioural sciences, and presents novel tools for research.

Getting to know each other - Artificial social intelligence for autonomous robots