aboutsummaryrefslogtreecommitdiff
path: root/README.md
diff options
context:
space:
mode:
authorPaul Oliver <contact@pauloliver.dev>2024-02-29 19:20:22 +0100
committerPaul Oliver <contact@pauloliver.dev>2024-02-29 19:20:52 +0100
commitaf7e23ab119eba7c0579796abd288c027edabfa9 (patch)
treefcd18c9405f33bed0e5f706a8a5d249ee3a63201 /README.md
Initial commitHEADmaster
Diffstat (limited to 'README.md')
-rw-r--r--README.md20
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