# NeuroPAL: Punctuated Anytime Learning with Neuroevolution for Macromanagement in Starcraft: Brood War

arXiv: https://arxiv.org/abs/2506.10384 · HTML: https://mlsanity.com/paper/2506.10384/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 12 Jun 2025.

## Builds on (most cited first, 6 of 6)

- [Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges](https://mlsanity.com/paper/2006.05415/) (2020)
- [StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer Learning](https://mlsanity.com/paper/1804.00810/) (2018)
- [MSC: A Dataset for Macro-Management in StarCraft II](https://mlsanity.com/paper/1710.03131/) (2017)
- [Macro action selection with deep reinforcement learning in StarCraft](https://mlsanity.com/paper/1812.00336/) (2018)
- [Learning Macromanagement in StarCraft from Replays using Deep Learning](https://mlsanity.com/paper/1707.03743/) (2017)
- [SIM2REALVIZ: Visualizing the Sim2Real Gap in Robot Ego-Pose Estimation](https://mlsanity.com/paper/2109.11801/) (2021)

## Abstract (arXiv)

StarCraft: Brood War remains a challenging benchmark for artificial intelligence research, particularly in the domain of macromanagement, where long-term strategic planning is required. Traditional approaches to StarCraft AI rely on rule-based systems or supervised deep learning, both of which face limitations in adaptability and computational efficiency. In this work, we introduce NeuroPAL, a neuroevolutionary framework that integrates Neuroevolution of Augmenting Topologies (NEAT) with Punctuated Anytime Learning (PAL) to improve the efficiency of evolutionary training. By alternating between frequent, low-fidelity training and periodic, high-fidelity evaluations, PAL enhances the sample efficiency of NEAT, enabling agents to discover effective strategies in fewer training iterations. We evaluate NeuroPAL in a fixed-map, single-race scenario in StarCraft: Brood War and compare its performance to standard NEAT-based training. Our results show that PAL significantly accelerates the learning process, allowing the agent to reach competitive levels of play in approximately half the training time required by NEAT alone. Additionally, the evolved agents exhibit emergent behaviors such as proxy barracks placement and defensive building optimization, strategies commonly used by expert human players. These findings suggest that structured evaluation mechanisms like PAL can enhance the scalability and effectiveness of neuroevolution in complex real-time strategy environments.