Derivative free optimization
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration
npx -y skills add a5c-ai/babysitter --skill derivative-free-optimizationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Optimization without gradient information
SKILL.md
1.2 KB, as published. Nobody here has run it
Derivative-Free Optimization
Purpose
Provides optimization capabilities for problems where gradient information is unavailable or unreliable.
Capabilities
- Nelder-Mead simplex method
- Powell's method
- Surrogate-based optimization
- Bayesian optimization
- Pattern search methods
- Trust region methods
Usage Guidelines
- Method Selection: Choose based on problem characteristics
- Function Evaluations: Minimize expensive function calls
- Surrogate Models: Build and refine surrogate approximations
- Exploration-Exploitation: Balance search strategies
Tools/Libraries
- scipy.optimize
- Optuna
- GPyOpt