Explaining Evolutionary Agent-Based Models via Principled Simplification


Understanding how evolutionary agents behave in complex environments is a challenging problem. Agents can be faced with complex fitness landscapes derived from multi-stage tasks, interaction with others, and limited environmental feedback. Agents that evolve to overcome these can sometimes access greater fitness, as a result of factors such as cooperation and tool use. However, it is often difficult to explain why evolutionary agents behave in certain ways, and what specific elements of the environment or task may influence the ability of evolution to find goal-achieving behaviours; even seemingly simple environments or tasks may contain features that affect agent evolution in unexpected ways. We explore principled simplification of evolutionary agent-based models, as a possible route to aiding their explainability. Using the River Crossing Task (RCT) as a case study, we draw on analysis in the Minimal River Crossing (RC-) Task testbed, which was designed to simplify the original task while keeping its key features. Using this method, we present new analysis concerning when agents evolve to successfully complete the RCT. We demonstrate that the RC- environment can be used to understand the effect that a cost to movement has on agent evolution, and that these findings can be generalised back to the original RCT. Then, we present new insight into the use of principled simplification in understanding evolutionary agents. We find evidence that behaviour dependent on features that survive simplification, such as problem structure, are amenable to prediction; while predicting behaviour dependent on features that are typically reduced in simplification, such as scale, can be invalid.

Publication DOI: https://doi.org/10.1162/artl_a_00339
Additional Information: © 2021 Massachusetts Institute of Technology. This is the author’s final version of 'Explaining Evolutionary Agent-Based Models via Principled Simplification' which has been accepted for publication in Artificial Life.
Uncontrolled Keywords: Evolutionary agents,Evolutionary algorithms,Explainability,Neuroevolution,Principled simplification,River crossing,Biochemistry, Genetics and Molecular Biology(all),Artificial Intelligence
Publication ISSN: 1530-9185
Last Modified: 20 May 2024 07:37
Date Deposited: 15 Sep 2021 08:11
Full Text Link:
Related URLs: https://direct. ... ased-Models-via (Publisher URL)
http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Article
Published Date: 2021-09-01
Published Online Date: 2021-09-01
Accepted Date: 2021-04-01
Authors: Barnes, Chloe M.
Ghouri, Abida
Lewis, Peter R.



Version: Accepted Version

| Preview

Export / Share Citation


Additional statistics for this record