Population-Based Training Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Core papers on population-based training and related population-driven methods for hyperparameter and policy optimization.

Population-Based Training: 10 key papers

1. Population Based Training of Neural Networks
   Jaderberg et al. arXiv 2017.
2. Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
   Jaderberg et al. arXiv 2018.
3. Population based Reinforcement Learning
   Pretorius and Pillay. 2021.
4. Evolution Strategies as a Scalable Alternative to Reinforcement Learning
   Salimans et al. arXiv 2017.
5. Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
   Such et al. arXiv 2017.
6. Faster Improvement Rate Population Based Training
   Dalibard and Jaderberg. arXiv 2021.
7. Sample-Efficient Automated Deep Reinforcement Learning
   Franke et al. arXiv 2020.
8. Open-Ended Learning Leads to Generally Capable Agents
   Stooke et al. arXiv 2021.
9. Collaborative Evolutionary Reinforcement Learning
   Khadka et al. arXiv 2019.
10. Evolving Reinforcement Learning Algorithms
    Co-Reyes et al. arXiv 2021.

Related reading lists

• Self-Play & Population-Based Training
• Hyperparameter Optimization & AutoML
• Mean-Field Games & Mean-Field Control
• Game Theory for Multi-Agent Systems
• Unsupervised Environment Design
• Curriculum Learning & Teacher-Student
• Offline-to-Online RL & Fine-Tuning
• LLM Agents & Tool-Augmented Language Models