Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
genetic_algorithm [2018/03/16 20:35]
admin
genetic_algorithm [2018/07/18 23:34]
admin
Line 123: Line 123:
  
 https://​eng.uber.com/​deep-neuroevolution/​ https://​eng.uber.com/​deep-neuroevolution/​
 +
 +https://​arxiv.org/​pdf/​1806.08099v1.pdf Lamarckian Evolution of Convolutional Neural
 +Networks
 +
 +Instead of randomly initializing the network weights before training, it is
 +also possible to inherit the already learned weights of an ancestor network. This
 +inheritance of aquired traits is a form of lamarckian evolution which, while
 +rejected in biology, can prove useful in artificial evolution.
 +
 +https://​arxiv.org/​abs/​1806.05695v1 Evolving simple programs for playing Atari games
 +
 +Cartesian Genetic Programming (CGP) has previously shown capabilities in image processing tasks by evolving programs with a function set specialized for computer vision. A similar approach can be applied to Atari playing. Programs are evolved using mixed type CGP with a function set suited for matrix operations, including image processing, but allowing for controller behavior to emerge. While the programs are relatively small, many controllers are competitive with state of the art methods for the Atari benchmark set and require less training time. By evaluating the programs of the best evolved individuals,​ simple but effective strategies can be found.