Learning Swarm Behaviors using Grammatical Evolution and Behavior Trees

Authors: Aadesh Neupane, Michael Goodrich

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We empirically verify the algorithm s effectiveness on three different problems: single-source foraging, collective transport, and nest maintenance.
Researcher Affiliation Academia Aadesh Neupane and Michael Goodrich Brigham Young University, Provo, UT aadeshnpn@byu.edu, mike@cs.byu.edu
Pseudocode No The paper provides a BNF grammar for the swarm behaviors but does not include pseudocode or an explicitly labeled algorithm block for the GEESE-BT algorithm itself.
Open Source Code No The paper does not provide any concrete access information (e.g., specific repository link, explicit code release statement, or code in supplementary materials) for the described methodology.
Open Datasets No The paper describes simulated environments for foraging, collective transport, and nest maintenance, but it does not specify the use of a named public dataset or provide access information (link, DOI, formal citation) for any custom-created dataset.
Dataset Splits No The paper does not explicitly provide specific dataset split information (percentages, sample counts, or detailed methodology) for training, validation, and testing.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions 'a python-based BT implementation' but does not provide specific version numbers for Python or any other software libraries or solvers used in the experiments.
Experiment Setup Yes Parameters GEESE Number of Genomes Required to Trigger Genetic Operations, Parent-Selection Fitness + truncation, Elite-size 1, Mutation Probability 0.01, Crossover variable onepoint, Crossover Probability 0.9, Genome-Selection Diversity, Maximum Codon Int 1000, Number of Agents 100, Behavior Sample 0.1 (Table 1: GEESE parameters used for the swarm experiments).