mlsanityData to 7 Oct 2026

Towards Futuristic Autonomous Experimentation--A Surprise-Reacting Sequential Experiment Policy

arXiv 2112.00600 ↗First posted 1 Dec 2021cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

An autonomous experimentation platform in manufacturing is supposedly capable of conducting a sequential search for finding suitable manufacturing conditions by itself or even for discovering new materials with minimal human intervention. The core of the intelligent control of such platforms is a policy to decide where to conduct the next experiment based on what has been done thus far. Such policy inevitably trades off between exploitation and exploration. Currently, the prevailing approach is to use various acquisition functions in the Bayesian optimization framework. We discuss whether it is beneficial to trade off exploitation versus exploration by measuring the element and degree of surprise associated with the immediate past observation. We devise a surprise-reacting policy using two existing surprise metrics, known as the Shannon surprise and Bayesian surprise. Our analysis shows that the surprise-reacting policy appears to be better suited for quickly characterizing the overall landscape of a response surface under resource constraints. We do not claim that we have a fully autonomous experimentation system but believe that the surprise-reacting capability benefits the automation of sequential decisions in autonomous experimentation.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 16 of its 77 references that are in the map. First posted on arXiv 1 Dec 2021.

Builds on

16 of 77 references.

References · 16

  1. 2018A Tutorial on Bayesian Optimizationcited by 734
  2. 2014Robots that can adapt like animalscited by 203
  3. 2019Bayesian Optimization for Materials Design with Mixed Quantitative and Qualitative Variablescited by 64
  4. 2017Improving the Expected Improvement Algorithmcited by 54
  5. 2019Greed is Good: Exploration and Exploitation Trade-offs in Bayesian Optimisationcited by 47
  6. 2021Benchmarking the Performance of Bayesian Optimization across Multiple Experimental Materials Science Domainscited by 46
  7. 2014Optimal Exploration-Exploitation in a Multi-Armed-Bandit Problem with Non-stationary Rewardscited by 41
  8. 2020Autonomous discovery in the chemical sciences part II: Outlookcited by 26
  9. 2020Autonomous discovery in the chemical sciences part I: Progresscited by 25
  10. 2019Why Non-myopic Bayesian Optimization is Promising and How Far Should We Look-ahead? A Study via Rolloutcited by 23
  11. 2020Efficient Rollout Strategies for Bayesian Optimizationcited by 19
  12. 2020Autonomous Materials Discovery Driven by Gaussian Process Regression with Inhomogeneous Measurement Noise and Anisotropic Kernelscited by 17
4 more
  1. 2019Gaussian Process Assisted Active Learning of Physical Lawscited by 14
  2. 2019A hierarchical expected improvement method for Bayesian optimizationcited by 13
  3. 2021A Robust Asymmetric Kernel Function for Bayesian Optimization, with Application to Image Defect Detection in Manufacturing Systemscited by 6
  4. 2019Adaptive design for Gaussian process regression under censoringcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 1.

4 papers.

  1. 2024An Augmented Surprise-guided Sequential Learning Framework for Predicting the Melt Pool Geometrycited by 6
  2. 2023Guiding the Sequential Experiments in Autonomous Experimentation Platforms through EI-based Bayesian Optimization and Bayesian Model Averagingcited by 3
  3. 2023Accelerating material discovery with a threshold-driven hybrid acquisition policy-based Bayesian optimizationcited by 3
  4. 2025From Automation to Autonomy in Smart Manufacturing: A Bayesian Optimization Framework for Modeling Multi-Objective Experimentation and Sequential Decision Makingcited by 1