This library provides several ways of describing a finite Markov Decision Process (MDP) model (see FiniteMDP::Model) and some reasonably efficient implementations of policy iteration and value iteration to solve it (see FiniteMDP::Solver).

Required Ruby Version

>= 0

Authors

John Lees-Miller

Versions

  1. 0.4.0

    1. source

      1. 0.4.0 source December 18, 2017 (19 KB)
  2. 0.3.0

    1. source

      1. 0.3.0 source October 09, 2016 (19 KB)
  3. 0.2.0

    1. source

      1. 0.2.0 source August 05, 2016 (17.5 KB)
  4. 0.1.1

    1. source

      1. 0.1.1 source February 13, 2012 (15.5 KB)
  5. 0.0.1

    1. source

      1. 0.0.1 source April 17, 2011 (14.5 KB)

SHA 256 checksum

← Previous version