Maximin-projection learning (MPL, Shi, et al., 2018) is implemented for recommending a meaningful and reliable individualized treatment regime for future groups of patients based on the observed data from different populations with heterogeneity in individualized decision making. Q-learning and A-learning are implemented for estimating the groupwise contrast function that shares the same marginal treatment effects. The packages contains classical Q-learning and A-learning algorithms for a single stage study as a byproduct.
| Package: | ITRLearn |
| Type: | Package |
| Version: | 1.0-1 |
| Date: | 2018-11-14 |
| License: | GPL-2 |
Shi, C., Song, R., Lu, W., and Fu, B. (2018). Maximin Projection Learning for Optimal Treatment Decision with Heterogeneous Individualized Treatment Effects. Journal of the Royal Statistical Society, Series B, 80: 681-702.