Solver for Partially Observable Markov Decision Processes (POMDP)

Provides the infrastructure to define and analyze the solutions of Partially Observable Markov Decision Processes (POMDP) models. The package includes pomdp-solve to solve POMDPs using a variety of exact and approximate value iteration algorithms. Smallwood and Sondik (1973) .

by Hossein Kamalzadeh and Michael Hahsler

Provides an interface to pomdp-solve, a solver for Partially Observable Markov Decision Processes (POMDP) origninally written by Anthony R. Cassandra. The package enables the user to simply define all components of a POMDP model and solve the problem using the finite grid method. The package also contains functions to analyze and visualize the solutions (e.g., the optimal policy).


pomdp 0.9.1 (01/02/2019)


  • Fixed Warning in fg-params.c

New Features

  • New method transitions to extract the transition matrix from a POMDP.

pomdp 0.9.0 (12/25/2018)

Initial CRAN release.

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


0.99.3 by Michael Hahsler, 3 months ago

Report a bug at

Browse source code at

Authors: Michael Hahsler [aut, cph, cre] , Hossein Kamalzadeh [aut, cph] , Anthony R. Cassandra [ctb, cph]

Documentation:   PDF Manual  

GPL (>= 3) license

Imports igraph

Suggests knitr, rmarkdown, testthat, Ternary, visNetwork, sarsop

See at CRAN