pomdp: Infrastructure for Partially Observable Markov Decision Processes (POMDP)

Provides the infrastructure to define and analyze the solutions of Partially Observable Markov Decision Process (POMDP) models. Interfaces for various exact and approximate solution algorithms are available including value iteration, point-based value iteration and SARSOP. Smallwood and Sondik (1973) <doi:10.1287/opre.21.5.1071>.

Version: 1.1.3
Depends: R (≥ 3.5.0)
Imports: pomdpSolve (≥ 1.0.4), processx, stats, methods, Matrix, Rcpp, foreach, igraph
LinkingTo: Rcpp
Suggests: knitr, rmarkdown, testthat, Ternary, visNetwork, sarsop, doParallel
Published: 2023-12-21
Author: Michael Hahsler ORCID iD [aut, cph, cre], Hossein Kamalzadeh [ctb]
Maintainer: Michael Hahsler <mhahsler at lyle.smu.edu>
BugReports: https://github.com/mhahsler/pomdp/issues
License: GPL (≥ 3)
Copyright: Copyright (C) Michael Hahsler and Hossein Kamalzadeh.
URL: https://github.com/mhahsler/pomdp
NeedsCompilation: yes
SystemRequirements: C++17
Classification/ACM: G.4, G.1.6, I.2.6
Citation: pomdp citation info
Materials: README NEWS
CRAN checks: pomdp results

Documentation:

Reference manual: pomdp.pdf
Vignettes: POMDP: Introduction to Partially Observable Markov Decision Processes

Downloads:

Package source: pomdp_1.1.3.tar.gz
Windows binaries: r-devel: pomdp_1.1.3.zip, r-release: pomdp_1.1.3.zip, r-oldrel: pomdp_1.1.3.zip
macOS binaries: r-release (arm64): pomdp_1.1.3.tgz, r-oldrel (arm64): pomdp_1.1.3.tgz, r-release (x86_64): pomdp_1.1.3.tgz
Old sources: pomdp archive

Reverse dependencies:

Reverse suggests: pomdpSolve

Linking:

Please use the canonical form https://CRAN.R-project.org/package=pomdp to link to this page.