Learn optimal policies via doubly robust empirical welfare maximization over trees. Given reward estimates, the algorithm finds a rule-based treatment allocation, where the policy takes the form of a shallow decision tree that is globally optimal (or nearly so). Methods are described in Sverdrup, Kanodia, Zhou, Athey, and Wager (2020) <doi:10.21105/joss.02232>, Athey and Wager (2021) <doi:10.3982/ECTA15732>, and Zhou, Athey, and Wager (2023) <doi:10.1287/opre.2022.2271>.
| Version: | 1.2.5 |
| Depends: | R (≥ 3.5.0) |
| Imports: | Rcpp, grf (≥ 2.0.0) |
| LinkingTo: | Rcpp, BH |
| Suggests: | testthat (≥ 3.0.4), DiagrammeR |
| Published: | 2026-08-04 |
| DOI: | 10.32614/CRAN.package.policytree |
| Author: | Erik Sverdrup [aut, cre], Ayush Kanodia [aut], Zhengyuan Zhou [aut], Susan Athey [aut], Stefan Wager [aut] |
| Maintainer: | Erik Sverdrup <erik.sverdrup at gmail.com> |
| BugReports: | https://github.com/grf-labs/policytree/issues |
| License: | MIT + file LICENSE |
| URL: | https://github.com/grf-labs/policytree |
| NeedsCompilation: | yes |
| In views: | CausalInference |
| CRAN checks: | policytree results |
| Reference manual: | policytree.html , policytree.pdf |
| Package source: | policytree_1.2.5.tar.gz |
| Windows binaries: | r-devel: policytree_1.2.4.zip, r-release: policytree_1.2.5.zip, r-oldrel: policytree_1.2.4.zip |
| macOS binaries: | r-release (arm64): policytree_1.2.5.tgz, r-oldrel (arm64): policytree_1.2.5.tgz, r-release (x86_64): policytree_1.2.5.tgz, r-oldrel (x86_64): policytree_1.2.5.tgz |
| Old sources: | policytree archive |
| Reverse imports: | EpiForsk, forestsearch, polle |
| Reverse suggests: | fastpolicytree, grf |
Please use the canonical form https://CRAN.R-project.org/package=policytree to link to this page.