ABSTRACT
A common aim in evolutionary search is to skillfully navigate complex search spaces. Achieving this aim requires creating search algorithms that exploit the structure of such spaces. Yet studying such structure directly is challenging because of the expansiveness of most search spaces. In the context of evolutionary robotics, this paper suggests a middle-ground approach that combines a full-fledged domain with an expressive but limited encoding, and then precomputes the behavior of all possible individuals, enabling evaluation as a look-up table. The product is an experimental playground in which search is non-trivial yet which offers extreme computational efficiency and ground truth about search-space structure. This paper describes the approach and demonstrates a range of its applications, directly exploring deception, behavioral rarity, and generalizations of evolvability in a popular benchmark task. The hope is that the extensible framework enables quick experimentation and idea generation, aiding brainstorming of new search algorithms and measures.
Supplemental Material
Available for Download
Supplemental files.
- Joel Lehman and Kenneth O. Stanley. Abandoning objectives: Evolution through the search for novelty alone. Evolutionary Computation, 19(2):189--223, 2011. Google ScholarDigital Library
- Terry Jones and Stephanie Forrest. Fitness distance correlation as a measure of problem didculty for genetic algorithms. 1995.Google Scholar
- M. Kirschner and J. Gerhart. Evolvability. Proceedings of the National Academy of Sciences of the United States of America, 95(15):8420, 1998.Google ScholarCross Ref
- Henok Mengistu, Joel Lehman, and Jeff Clune. Evolvability search: Directly selecting for evolvability in order to study and produce it. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2016). ACM, 2016. Google ScholarDigital Library
- Joel Lehman and Kenneth O. Stanley. Beyond open-endedness: Quantifying impressiveness. In Proceedings of Artificial Life Thirteen (ALIFE XIII), 2012.Google ScholarCross Ref
Index Terms
Precomputation for rapid hypothesis generation in evolutionary robotics
Recommendations
Enhancing Divergent Search through Extinction Events
GECCO '15: Proceedings of the 2015 Annual Conference on Genetic and Evolutionary ComputationA challenge in evolutionary computation is to create representations as evolvable as those in natural evolution. This paper hypothesizes that extinction events, i.e. mass extinctions, can significantly increase evolvability, but only when combined with ...
On Evolvability and Behavior Landscapes in Neuroevolutionary Divergent Search
GECCO '23: Proceedings of the Genetic and Evolutionary Computation ConferenceEvolvability refers to the ability of an individual genotype (solution) to produce offspring with mutually diverse phenotypes. Recent research has demonstrated that divergent search methods, particularly novelty search, promote evolvability by ...
Coupling novelty and surprise for evolutionary divergence
GECCO '17: Proceedings of the Genetic and Evolutionary Computation ConferenceDivergent search techniques applied to evolutionary computation, such as novelty search and surprise search, have demonstrated their efficacy in highly deceptive problems compared to traditional objective-based fitness evolutionary processes. While ...
Comments