diff options
author | Paul Oliver <contact@pauloliver.dev> | 2024-02-29 19:20:22 +0100 |
---|---|---|
committer | Paul Oliver <contact@pauloliver.dev> | 2024-02-29 19:20:52 +0100 |
commit | af7e23ab119eba7c0579796abd288c027edabfa9 (patch) | |
tree | fcd18c9405f33bed0e5f706a8a5d249ee3a63201 /README.md |
Diffstat (limited to 'README.md')
-rw-r--r-- | README.md | 20 |
1 files changed, 20 insertions, 0 deletions
diff --git a/README.md b/README.md new file mode 100644 index 0000000..4c624f8 --- /dev/null +++ b/README.md @@ -0,0 +1,20 @@ +This program was created for the sole purpose of testing my implementation of +the rtES-HyperNeat algorithm. The idea is to generate a set of racer-agents +that must learn to race proficiently around a track. Several tests have been +designed, each with different challenges. + +- [YouTube Playlist](https://www.youtube.com/watch?v=JeXqbYXKqcs&list=PLrEmYrpTcDJb_RfwCpSnCPk1Cus310ehA) +- [Featured on Evolutionary Complexity (EPlex) Research Group](http://eplex.cs.ucf.edu/ESHyperNEAT/) + +rtES-HyperNeat (Real Time Evolving Substrate Hypercube based Neuro-Evolution of +Augmenting Topologies) is a real time neuro-evolution algorithm based on the +papers written by Kenneth Stanley and other researchers at the EPLEX group +(http://eplex.cs.ucf.edu/). More specifically, rtES-HyperNeat tries to blend the +existing ES-HyperNeat (http://eplex.cs.ucf.edu/ESHyperNEAT/) algorithm with +rtNeat (http://nn.cs.utexas.edu/?rtNEAT), a previous version which allowed real +time evolution of agents on a virtual field. The main problem with trying to +make ES-HyperNeat real-timed was that the CPPNs (genotypes) had to be converted +into functional Neural Networks (phenotypes) on a single time-step. This was +proven to be impossible, so, as a solution, the library handles these +transformations on separate execution threads. This way, the algorithm flows +seamlessly.
\ No newline at end of file |