Download
Agent Executor (AX) is a Google research project for learning discrete choice models through differentiable maximum likelihood estimation. It is designed for situations where a model needs to predict choices from a finite set of alternatives, such as ranking, recommendation, preference modeling, or decision behavior analysis. The project provides JAX-based tools for defining and training choice models with automatic differentiation. It focuses on flexible model construction rather than a single fixed estimator, making it useful for researchers who want to experiment with different utility functions and optimization setups. ax is especially relevant for machine learning and econometrics workflows that need scalable, differentiable approaches to choice modeling. Its main value is giving researchers a modern, accelerator-friendly framework for estimating and analyzing discrete choice behavior.
Features
- JAX-based discrete choice modeling toolkit
- Differentiable maximum likelihood estimation
- Support for custom utility model definitions
- Designed for ranking and preference-learning research
- Automatic differentiation for scalable optimization
- Useful for recommendation, econometrics, and decision modeling
Project Samples
