Citation

BibTex format

@inproceedings{Tarapore:2016:10.1145/2908812.2908875,
author = {Tarapore, D and Clune, J and Cully, AHR and Mouret, J-B},
doi = {10.1145/2908812.2908875},
pages = {173--180},
publisher = {ACM},
title = {How do different encodings influence the performance of the MAP-Elites algorithm?},
url = {http://dx.doi.org/10.1145/2908812.2908875},
year = {2016}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - 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.
AU - Tarapore,D
AU - Clune,J
AU - Cully,AHR
AU - Mouret,J-B
DO - 10.1145/2908812.2908875
EP - 180
PB - ACM
PY - 2016///
SP - 173
TI - How do different encodings influence the performance of the MAP-Elites algorithm?
UR - http://dx.doi.org/10.1145/2908812.2908875
UR - http://hdl.handle.net/10044/1/48647
ER -

Contact us

Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ

To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:

ai-speaker@imperial.ac.uk

To reach the network manager, Diana O'Malley - including to join the network - please contact:

ai-net-manager@imperial.ac.uk