Transfer Dynamics in Emergent Evolutionary Curricula

Aaron Dharna, Amy K. Hoover, Julian Togelius, Lisa Soros

Research output: Contribution to journalArticlepeer-review


PINSKY is a system for open-ended learning through neuroevolution in game-based domains. It builds on the Paired Open-Ended Trailblazer (POET) system, which originally explored learning and environment generation for bipedal walkers, and adapts it to games in the General Video Game AI (GVGAI) system. Previous work showed that by co-evolving levels and neural network policies, levels could be found for which successful policies could not be created via optimization alone. Studied in the realm of Artificial Life as a potentially open-ended alternative to gradient-based fitness, minimal criteria (MC)-based selection helps foster diversity in evolutionary populations. The main question addressed by this paper is how the open-ended learning actually works, focusing in particular on the role of transfer of policies from one evolutionary branch ("species") to another. We analyze the dynamics of the system through creating phylogenetic trees, analyzing evolutionary trajectories of policies, and temporally breaking down transfers according to species type. Furthermore, we analyze the impact of the minimal criterion on generated level diversity and inter-species transfer. The most insightful finding is that inter-species transfer, while rare, is crucial to the system's success.

Original languageAmerican English
JournalIEEE Transactions on Games
StateAccepted/In press - 2022

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering


  • Games
  • Optimization
  • Sociology
  • Statistics
  • Task analysis
  • Training
  • Transfer learning
  • Transfer learning
  • curriculum learning
  • neural networks


Dive into the research topics of 'Transfer Dynamics in Emergent Evolutionary Curricula'. Together they form a unique fingerprint.

Cite this