On the huge benefit of quasi-random mutations for multimodal optimization with application to grid-based tuning of neurocontrollers

Guillaume Chaslot 1 Jean-Baptiste Hoock 2 Fabien Teytaud 2, 3, 4 Olivier Teytaud 2, 3, 4
2 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
3 TANC - Algorithmic number theory for cryptology
LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau], Inria Saclay - Ile de France
Abstract : In this paper, we study the optimization of a neural network used for controlling a Monte-Carlo Tree Search (MCTS/UCT) algorithm. The main results are: (i) the specification of a new multimodal benchmark function; this function has been defined in particular in agreement with [1] which has pointed out that most multimodal functions are not satisfactory for some real-world multimodal scenarios (section 2); (ii) experimentation of Evolution Strategies on this new multimodal benchmark function, showing the great efficiency of quasi-random mutations in this framework (section 3); (iii) the proof-of-concept of the application of ES for grid-based tuning Neural Networks for controlling MCTS/UCT (see section 3).
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download

https://hal.inria.fr/inria-00380125
Contributor : Fabien Teytaud <>
Submitted on : Thursday, April 30, 2009 - 9:00:21 AM
Last modification on : Wednesday, March 27, 2019 - 4:41:29 PM
Long-term archiving on : Thursday, June 10, 2010 - 6:51:53 PM

File

qrll.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00380125, version 1

Collections

Citation

Guillaume Chaslot, Jean-Baptiste Hoock, Fabien Teytaud, Olivier Teytaud. On the huge benefit of quasi-random mutations for multimodal optimization with application to grid-based tuning of neurocontrollers. ESANN, Apr 2009, Bruges, Belgium. ⟨inria-00380125⟩

Share

Metrics

Record views

951

Files downloads

517