Download:
|
by Kenneth O. Stanley, Risto Miikkulainen
In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO2002
ftp://ftp.cs.utexas.edu/pub/neural-nets/papers/stanley.gecco02_2.ps.Z
Add To MetaCart
Abstract:
In competitive coevolution, the goal is to establish an "arms race " that will lead to increasingly sophisticated strategies. However, in practice, the process often leads to idiosyncrasies rather than continual improvement. Applying the NEAT method for evolving neural networks to a competitive simulated robot duel domain, we will demonstrate that (1) as evolution progresses the networks become more complex, (2) complexification elaborates on existing strategies, and (3) if NEAT is allowed to complexify, it finds dramatically more sophisticated strategies than when it is limited to fixed-topology networks. The results suggest that in order to realize the full potential of competitive coevolution, genomes must be allowed to complexify as well as optimize over the course of evolution. 1
Citations
|
387
|
Genetic algorithms with sharing for multi-modal function optimization
– Goldberg, Richardson
- 1987
|
|
218
|
Evolving artificial neural networks
– Yao
- 1999
|
|
159
|
An evolutionary algorithm that constructs recurrent neural networks
– Angeline, Saunders, et al.
- 1993
|
|
127
|
Competitive environments evolve better solutions for complex tasks
– Angeline, Pollack
- 1993
|
|
125
|
Mobile robot miniaturization: A tool for investigation in control algorithms
– Mondada, Franzi, et al.
- 1993
|
|
97
|
Evolving neural networks through augmenting topologies
– Stanley, Miikkulainen
|
|
86
|
Incremental evolution of complex general behavior
– Gomez, Miikkulainen
- 1997
|
|
74
|
A comparison between cellular encoding and direct encoding for genetic neural networks
– Gruau, Whitley, et al.
- 1996
|
|
50
|
Arms races between and within species
– Dawkins, Krebs
- 1979
|
|
47
|
God save the red queen! competition in coevolutionary robotics
– FLOREANO, NOLFI
- 1997
|
|
46
|
Genetic set recombination and its application to neural network topology optimisation
– Radcliffe
- 1993
|
|
26
|
Efficient reinforcement learning through evolving neural network topologies
– Stanley, Miikkulainen
- 2002
|
|
23
|
Co-Evolutionary Learning by Automatic Modularisation with Speciation
– Darwen
- 1996
|
|
22
|
Co-evolution of pursuit and evasion I: Biological and game-theoretic foundations
– Miller, Cliff
- 1994
|
|
20
|
The dominance tournament method of monitoring progress in coevolution
– Stanley, Miikkulainen
- 2002
|
|
14
|
Efficient Evolution of Neural Network Topologies
– Stanley, Miikkulainen
- 2002
|
|
13
|
Talking helps: Evolving communicating agents for the predator-prey pursuit problem
– Jim, Giles
|
|
9
|
New methods for competitive evolution
– Rosin, Belew
- 1997
|
|
6
|
A new evolutionary law. Evolution Theory
– Valin
- 1973
|
|
4
|
Speculations on the early course of evolution
– Darnell, Doolittle
- 1986
|
|
4
|
Conditions enabling the evolution of inter-agent signaling in an artificial world
– Reggia, Schulz, et al.
- 2001
|
