Overview
The package builds on GPyTorch and BoTorch and documents mixed parameter spaces, constraints and multi-objective optimization. Its ask–tell interface separates suggested experiments from externally supplied measurements and can work with Olympus.
Atlas is a distinct optimization project, unrelated to the ChemAI Atlas directory. Its README currently recommends Python 3.9/3.10 and excludes 3.11+. MIT covers code; instrument execution and suitability for a specific experiment require separate integration and evaluation.
Key Features
- Gaussian-process Bayesian experiment planning
- Mixed domains, constraints and multiple objectives
Use Cases
- Optimize experimental conditions through an ask–tell loop with recorded measurements.
How to Use
- Read the official instructions and select the documented task and environment.
- Obtain only the required data or checkpoints and check their specific terms.
- Evaluate a small representative example against references before adapting the workflow. These steps have not been run during curation.
Sources and verification
This entry describes capabilities documented by the linked project sources. Catalog edits are not evidence of a successful run, compatibility test or scientific performance evaluation.
Read the editorial and verification policy