Human-in-the-Loop Interpretable Reinforcement Learning via Evolutionary Decision Trees

Created by W.Langdon from gp-bibliography.bib Revision:1.9194

@InProceedings{Zhan:2026:ECXAI,

• author = "Hao Jie Zhan and Stefano Genetti and Giovanni Iacca",
• title = "Human-in-the-Loop Interpretable Reinforcement Learning via Evolutionary Decision Trees",
• booktitle = "Evolutionary Computing and Explainable Artificial Intelligence (ECXAI)",
• year = "2026",
• editor = "Jaume Bacardit and Alexander Brownlee and Stefano Cagnoni and Martin Fyvie and Giovanni Iacca and David Walker",
• address = "Trento, Italy",
• month = "29 " # aug,
• keywords = "genetic algorithms, genetic programming, Interpretable AI, XAI, Human-in-the-loop optimization, Evolutionary Reinforcement Learning, Decision Trees, DT, Interactive Evolutionary Computation, IET",
• URL = "https://ecxai.github.io/ecxai/ppsn2026/PPSN-ECXAI_2026_paper_3.pdf",
• size = "5 pages",
• abstract = "we present ieldt (Interactive Evolutionary Learning of interpretable Decision Trees), a novel framework that integrates Evolutionary Reinforcement Learning with a rich human-driven refinement interface. IELDT evolves populations of interpretable decision tree policies and periodically exposes the best-performing tree to a domain expert through an intuitive web interface, allowing manual or natural-language-guided edits. The human-crafted policy is then re-injected into the evolutionary loop via a Lamarckian genotype reconstruction algorithm. The framework will be released as an open-source, modular Python library compatible with the OpenAI Gym interface, facilitating broad adoption and applicability",
• notes = "https://ecxai.github.io/ecxai/workshop-ppsn-2026.html Workshop on Evolutionary Computing and Explainable AI @PPSN 2026",

}

Genetic Programming entries for Hao Jie Zhan Stefano Genetti Giovanni Iacca

Citations