How Do Different Encodings Influence the Performance of the MAP-Elites Algorithm?

Abstract : The recently introduced Intelligent Trial and Error algorithm (IT&E) both improves the ability to automatically generate controllers that transfer to real robots, and enables robots to creatively adapt to damage in less than 2 minutes. A key component of IT&E is a new evolutionary algorithm called MAP-Elites, which creates a behavior-performance map that is provided as a set of " creative " ideas to an online learning algorithm. To date, all experiments with MAP-Elites have been performed with a directly encoded list of parameters: it is therefore unknown how MAP-Elites would behave with more advanced encodings, like HyperNeat and SUPG. In addition, because we ultimately want robots that respond to their environments via sensors, we investigate the ability of MAP-Elites to evolve closed-loop controllers, which are more complicated, but also more powerful. Our results show that the encoding critically impacts the quality of the results of MAP-Elites, and that the differences are likely linked to the locality of the encoding (the likelihood of generating a similar behavior after a single mutation). Overall, these results improve our understanding of both the dynamics of the MAP-Elites algorithm and how to best harness MAP-Elites to evolve effective and adaptable robotic controllers.
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download

https://hal.inria.fr/hal-01302658
Contributor : Jean-Baptiste Mouret <>
Submitted on : Thursday, April 14, 2016 - 5:27:08 PM
Last modification on : Tuesday, December 18, 2018 - 4:40:22 PM
Long-term archiving on : Tuesday, November 15, 2016 - 3:48:59 AM

File

gecco_map_elites.pdf
Publication funded by an institution

Identifiers

Citation

Danesh Tarapore, Jeff Clune, Antoine Cully, Jean-Baptiste Mouret. How Do Different Encodings Influence the Performance of the MAP-Elites Algorithm?. Genetic and Evolutionary Computation Conference, 2016, Denver, United States. ⟨10.1145/2908812.2908875⟩. ⟨hal-01302658⟩

Share

Metrics

Record views

567

Files downloads

473