Distributed Embodied Evolution in Networks of Agents

@article{Yaman2021DistributedEE,
  title={Distributed Embodied Evolution in Networks of Agents},
  author={Anil Yaman and Giovanni Iacca},
  journal={Appl. Soft Comput.},
  year={2021},
  volume={101},
  pages={106993}
}
View PDF on arXiv
2 Citations
Background Citations
1

Figures from this paper

2 Citations

Meta-control of social learning strategies
TLDR
It is shown that while the success-based strategy fully exploits the benign environment of low uncertainly, it fails in uncertain environments, and the conformist strategy can effectively mitigate this adverse effect.
Emergence and Diffusion of Novel Associative Ideas in a Multi-Agent Network Model of Implicit Learning

References

SHOWING 1-10 OF 53 REFERENCES
Environment-driven distributed evolutionary adaptation in a population of autonomous robotic agents
TLDR
The proposed embodied evolutionary algorithm, termed mEDEA, is shown to be both efficient in unknown environments and robust to abrupt and unpredicted changes in the environment.
Influence of Local Selection and Robot Swarm Density on the Distributed Evolution of GRNs
TLDR
This paper uses dEE to evolve fixed-topology GRN swarm robot controllers for an item collection task, and uses a metric to quantify selection pressure in evolutionary systems, based on the correlation between number of offspring and fitness of the behaviors.
Real-time optimization of dynamic problems through distributed Embodied Evolution
TLDR
This work analyzes the canonical dEE response in a series of scenarios of increasing complexity related to two highly representative dynamic engineering problems: a Dynamic Fleet Size and Mix Vehicle Routing Problem with Time Windows (DFSMVRPTW) and a collective surveillance task with realistic location degradation.
Cellular Evolutionary Algorithms: Evaluating the Influence of Ratio
TLDR
It is found that, with the same neighborhood, rectangular grids have some advantages in multimodal and epistatic problems, while square ones are more efficient for solving deceptive problems and for simple function optimization.
Evolving Diverse Collective Behaviors Independent of Swarm Density
TLDR
An extended method called diverse-prediction is presented that rewards not only for correct predictions but also for each visited sensory state and proves to be a better approach compared to the method prediction that was reported before.
Behavioral Specialization in Embodied Evolutionary Robotics: Why So Difficult?
TLDR
This research sheds light on why existing embodied evolution algorithms are limited with respect to learning efficient division of labour in the general case, ie.
P 2 POEM : Function optimization in P 2 P networks
Scientists working in the area of distributed function optimization have to deal with a huge variety of optimization techniques and algorithms. Most of the existing research in this domain makes use…
A Framework for Distributed Evolutionary Algorithms
This paper describes the recently released DREAM (Distributed Resource Evolutionary Algorithm Machine) framework for the automatic distribution of evolutionary algorithm (EA) processing through a…
Distributed optimization in wireless sensor networks: an island-model framework
TLDR
This paper investigates the possibility to perform an online, distributed optimization process within a WSN, called DOWSN (distributed optimization for WSN), an island-model infrastructure in which each node executes a simple, computationally cheap optimization algorithm, and shares promising solutions with its neighbors.
p2poem: Function optimization in P2P networks
Scientists working in the area of distributed function optimization have to deal with a huge variety of optimization techniques and algorithms. Most of the existing research in this domain makes use…
...
...