MAP-Elites

tags
Quality diversity, Reinforcement learning
papers
(Mouret, Clune 2015; Cully et al. 2015)

MAP-Elites are an example of QD algorithm. The behavior space is discretized in cells and during exploration, only the best “elite” for each cell is kept.

Individuals are added to the grid if they:

  • fill an empty space
  • are better than an existing elite

Bibliography

  1. . . "Illuminating Search Spaces by Mapping Elites". Arxiv:1504.04909 [cs, Q-bio]. http://arxiv.org/abs/1504.04909.
  2. . . "Robots That Can Adapt Like Animals". Nature 521 (7553). Nature Publishing Group:503–7. DOI.
Last changed | authored by

Comments


← Back to Notes