# HEAS: Hierarchical Evolutionary Agent-Based Simulation Framework for Multi-Objective Policy Search

arXiv: https://arxiv.org/abs/2508.15555 · HTML: https://mlsanity.com/paper/2508.15555/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 33 references that are in the map.
- First posted on arXiv 21 Aug 2025.

## Builds on (most cited first, 2 of 2)

- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [PettingZoo: Gym for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2009.14471/) (2020)

## Built on by (most cited first, 1 of 1)

- [Metric Aggregation Divergence: A Hidden Validity Threat in Agent-Based Policy Optimization and a Contractual Remedy](https://mlsanity.com/paper/2606.29038/) (2026)

## Abstract (arXiv)

HEAS is a Python framework that connects agent-based simulation, evolutionary search, and scenario-based evaluation in a single reproducible pipeline. It is designed for researchers who study systems where local interactions produce system-level outcomes-ecosystems, organizations, markets, or regulatory environments-and who need to search over candidate strategies and compare them across uncertain scenarios. HEAS combines three modules: a hierarchy runtime for composing simulations from reusable process layers, an evolutionary tuner for single- or multi-objective search backed by DEAP, and a game module for evaluating strategies across scenario ensembles. Its central design principle is the "metric contract": the same outcome function is shared by optimization, evaluation, and validation, so that different parts of an analysis cannot silently rank strategies by different quantities.