Avoiding convergence in cooperative coevolution with novelty search

@inproceedings{Gomes2014AvoidingCI,
  title={Avoiding convergence in cooperative coevolution with novelty search},
  author={Jorge C. Gomes and Pedro Mariano and Anders Lyhne Christensen},
  booktitle={AAMAS},
  year={2014}
}
Cooperative coevolution is an approach for evolving solutions composed of coadapted components. Previous research has shown, however, that cooperative coevolutionary algorithms are biased towards stability: they tend to converge prematurely to equilibrium states, instead of converging to optimal or near-optimal solutions. In single-population evolutionary algorithms, novelty search has been shown capable of avoiding premature convergence to local optima - a pathology similar to convergence to… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 19 CITATIONS

Novelty-Driven Cooperative Coevolution

VIEW 13 EXCERPTS
CITES METHODS & BACKGROUND

Multi-agent Behavior-Based Policy Transfer

  • EvoApplications
  • 2016
VIEW 6 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Cooperative Co-Evolution-Based Design Optimization: A Concurrent Engineering Perspective

  • IEEE Transactions on Evolutionary Computation
  • 2018
VIEW 2 EXCERPTS
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 28 REFERENCES

Evolving team behaviors with specialization

  • Genetic Programming and Evolvable Machines
  • 2012
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

When Novelty Is Not Enough

  • EvoApplications
  • 2011
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Coevolution of Role-Based Cooperation in Multiagent Systems

  • IEEE Transactions on Autonomous Mental Development
  • 2009
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Biasing Coevolutionary Search for Optimal Multiagent Behaviors

  • IEEE Transactions on Evolutionary Computation
  • 2006
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL