# MRRNs

This repository implements Matching Regularized Regression Networks (MRRNs) for counterfactual inference 
on multiple continuous treatment options. The network architecture is an extension to TARNETs [1], using 
the treatment-concatenation technique from the BNN [2] architecture to introduce continuous treatment doses.
We add to the factual MSE loss an approximation of the counterfactual MSE, based on uniformly sampled doses
and a matching based approximation of the counterfactual outcome. (Possibly in propensity space.)

## Usage
Experiments can be defined as textfiles in the experimental_setup folder (an example is given).
then run:<br>
```python run_experiment.py experiment_name```

## References
[1] U. Shalit, F. D. Johansson, and D. Sontag, “Estimating individual treatment effect: generalization
bounds and algorithms,” in Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 3076–3085, 2017

[2] F. D. Johansson, U. Shalit, and D. Sontag, “Learning representations for counterfactual inference,”
in Proceedings of the 33rd International Conference on International Conference on Machine Learning, vol. 48, pp. 3020–3029, 2016