mlsanityData to 7 Oct 2026

Population Based Training of Neural Networks

arXiv 1711.09846 ↗First posted 27 Nov 2017cs.LG cs.NEcited by 351

Not on the map. Why?

Cited by 33 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Neural networks dominate the modern machine learning landscape, but their training and success still suffer from sensitivity to empirical choices of hyperparameters such as model architecture, loss function, and optimisation algorithm. In this work we present Population Based Training (PBT), a simple asynchronous optimisation algorithm which effectively utilises a fixed computational budget to jointly optimise a population of models and their hyperparameters to maximise performance. Importantly, PBT discovers a schedule of hyperparameter settings rather than following the generally sub-optimal strategy of trying to find a single fixed set to use for the whole course of training. With just a small modification to a typical distributed hyperparameter training framework, our method allows robust and reliable training of models. We demonstrate the effectiveness of PBT on deep reinforcement learning problems, showing faster wall-clock convergence and higher final performance of agents by optimising over a suite of hyperparameters. In addition, we show the same method can be applied to supervised learning for machine translation, where PBT is used to maximise the BLEU score directly, and also to training of Generative Adversarial Networks to maximise the Inception score of generated images. In all cases PBT results in the automatic discovery of hyperparameter schedules and model selection which results in stable training and better final performance.

Key facts. Cited by 351 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 2; 2021: 70; 2022: 53; 2023: 72; 2024: 30; 2025: 58; 2026: 66.

351 papers.

Sort:

By area:

  1. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  2. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 294
  3. 2023Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewardscited by 232
  4. 2021Open-Ended Learning Leads to Generally Capable Agentscited by 177
  5. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 173
  6. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 153
  7. 2021Collaborating with Humans without Human Datacited by 139
  8. 2023Human-Timescale Adaptation in an Open-Ended Task Spacecited by 136
  9. 2023End-to-End Speech Recognition: A Surveycited by 127
  10. 2020Hyperparameter Selection for Offline Reinforcement Learningcited by 113
  11. 2021AutoFlow: Learning a Better Training Set for Optical Flowcited by 102
  12. 2023ProAgent: Building Proactive Cooperative Agents with Large Language Modelscited by 97
38 more
  1. 2021From Motor Control to Team Play in Simulated Humanoid Footballcited by 87
  2. 2023Using Large Language Models for Hyperparameter Optimizationcited by 71
  3. 2021Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordinationcited by 69
  4. 2022Automated Reinforcement Learning (AutoRL): A Survey and Open Problemscited by 69
  5. 2021Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Datacited by 67
  6. 2023LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Modelscited by 65
  7. 2025Robust Autonomy Emerges from Self-Playcited by 64
  8. 2022Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progresscited by 63
  9. 2021On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learningcited by 59
  10. 2023A Unified, Scalable Framework for Neural Population Decodingcited by 59
  11. 2023Hyperparameters in Reinforcement Learning and How To Tune Themcited by 58
  12. 2021Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategiescited by 52
  13. 2021Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shapingcited by 51
  14. 2021Revisiting Design Choices in Offline Model-Based Reinforcement Learningcited by 50
  15. 2021Representation learning for neural population activity with Neural Data Transformerscited by 48
  16. 2022Discovering Evolution Strategies via Meta-Black-Box Optimizationcited by 44
  17. 2023OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Modelscited by 44
  18. 2024Enhance Reasoning for Large Language Models in the Game Werewolfcited by 44
  19. 2022Contextualize Me -- The Case for Context in Reinforcement Learningcited by 41
  20. 2022evosax: JAX-based Evolution Strategiescited by 39
  21. 2022Model Zoos: A Dataset of Diverse Populations of Neural Network Modelscited by 38
  22. 2021Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agentscited by 35
  23. 2021Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomizationcited by 35
  24. 2021Efficient Transformers in Reinforcement Learning using Actor-Learner Distillationcited by 35
  25. 2025MAT-Agent: Adaptive Multi-Agent Training Optimizationcited by 34
  26. 2022K-level Reasoning for Zero-Shot Coordination in Hanabicited by 30
  27. 2022On Implicit Bias in Overparameterized Bilevel Optimizationcited by 30
  28. 2023Cooperative Open-ended Learning Framework for Zero-shot Coordinationcited by 30
  29. 2023A Review of Cooperation in Multi-agent Learningcited by 27
  30. 2022A Dataset for Medical Instructional Video Classification and Question Answeringcited by 26
  31. 2024B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasonerscited by 26
  32. 2023PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordinationcited by 25
  33. 2026Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weightscited by 25
  34. 2021MedGPT: Medical Concept Prediction from Clinical Narrativescited by 24
  35. 2021A survey on multi-objective hyperparameter optimization algorithms for Machine Learningcited by 24
  36. 2023Evolutionary Reinforcement Learning: A Surveycited by 24
  37. 2023DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Trainingcited by 24
  38. 2024SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learningcited by 24

50 most cited of 351 All 351 (JSON)