PT-DCFR: Accelerating and Improving Deep CFR Using Population Based Training (Student Abstract)

Authors

  • Dingzhong Cai Northwestern Polytechnical University
  • Huale Li Lanzhou University
  • Hang Xiao Northwestern Polytechnical University
  • Shuhan Qi Harbin Institute of Technology
  • Jiajia Zhang Harbin Institute of Technology

DOI:

https://doi.org/10.1609/aaai.v40i48.42192

Abstract

Deep CFR enables end-to-end approximation of Nash equilibria in imperfect-information games(IIGs) but is sensitive to hyperparameters, making manual tuning inefficient. To address this, we propose PT-DCFR, which integrates Population-Based Training(PBT) with Deep CFR to dynamically optimize hyperparameters during training. Building upon this, we further introduce P2T-DCFR, which decouples parameter selection from model performance.
AAAI-26 / IAAI-26 / EAAI-26 Proceedings Cover

Downloads

Published

2026-03-14

How to Cite

Cai, D., Li, H., Xiao, H., Qi, S., & Zhang, J. (2026). PT-DCFR: Accelerating and Improving Deep CFR Using Population Based Training (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41143–41145. https://doi.org/10.1609/aaai.v40i48.42192

Issue

Vol. 40 No. 48: EAAI-26 AI for Education, Model AI Assignments, AAAI-26 Emerging Trends, Doctoral Consortium, Student Abstracts, Undergraduate Consortium and Demonstrations

Section

AAAI Student Abstract and Poster Program