Markov Decision Process (MDP) Toolbox for Python¶
The MDP toolbox provides classes and functions for the resolution of descrete-time Markov Decision Processes. The list of algorithms that have been implemented includes backwards induction, linear programming, policy iteration, q-learning and value iteration along with several variations.
The classes and functions were developped based on the MATLAB MDP toolbox by the Biometry and Artificial Intelligence Unit of INRA Toulouse (France). There are editions available for MATLAB, GNU Octave, Scilab and R. The suite of MDP toolboxes are described in Chades I, Chapron G, Cros M-J, Garcia F & Sabbadin R (2014) ‘MDPtoolbox: a multi-platform toolbox to solve stochastic dynamic programming problems’, Ecography, vol. 37, no. 9, pp. 916–920, doi 10.1111/ecog.00888.
PLEASE NOTE: the linear programming algorithm is currently unavailable except for testing purposes due to incorrect behaviour.
NumPy and SciPy must be on your system to use this toolbox. Please have a look at their documentation to get them installed. If you are installing onto Ubuntu or Debian and using Python 2 then this will pull in all the dependencies:
sudo apt-get install python-numpy python-scipy python-cvxopt
On the other hand, if you are using Python 3 then cvxopt will have to be compiled (pip will do it automatically). To get NumPy, SciPy and all the dependencies to have a fully featured cvxopt then run:
sudo apt-get install python3-numpy python3-scipy liblapack-dev libatlas-base-dev libgsl0-dev fftw-dev libglpk-dev libdsdp-dev
The two main ways of downloading the package is either from the Python Package Index or from GitHub. Both of these are explained below.
Python Package Index (PyPI)¶
The toolbox’s PyPI page is https://pypi.python.org/pypi/pymdptoolbox/ and there are both zip and tar.gz archive options available that can be downloaded. However, I recommend using pip to install the toolbox if you have it available. Just type
pip install pymdptoolbox
at the console and it should take care of downloading and installing everything for you. If you also want cvxopt to be automatically downloaded and installed so that you can help test the linear programming algorithm then type
pip install "pymdptoolbox[LP]"
If you want it to be installed just for you rather than system wide then do
pip install --user pymdptoolbox
If you downloaded the package manually from PyPI
Extract the *.zip or *.tar.gz archive
tar -xzvf pymdptoolbox-<VERSION>.tar.gz
Change to the PyMDPtoolbox directory
Install via Setuptools, either to the root filesystem or to your home directory if you don’t have administrative access.
python setup.py install
python setup.py install --user
Read the Setuptools documentation for more advanced information.
Of course you can also use virtualenv or simply just unpack it to your working directory.
Start Python in your favourite way. The following example shows you how to import the module, set up an example Markov decision problem using a discount value of 0.9, solve it using the value iteration algorithm, and then check the optimal policy.
import mdptoolbox.example P, R = mdptoolbox.example.forest() vi = mdptoolbox.mdp.ValueIteration(P, R, 0.9) vi.run() vi.policy # result is (0, 0, 0)
Documentation is available at http://pymdptoolbox.readthedocs.org/ and also as docstrings in the module code. If you use IPython to work with the toolbox, then you can view the docstrings by using a question mark ?. For example:
import mdptoolbox mdptoolbox?<ENTER> mdptoolbox.mdp?<ENTER> mdptoolbox.mdp.ValueIteration?<ENTER>
will display the relevant documentation.
Issue Tracker: https://github.com/sawcordwell/pymdptoolbox/issues
Source Code: https://github.com/sawcordwell/pymdptoolbox
Use the issue tracker.
- Markov Decision Process (MDP) Toolbox
- Markov Decision Process (MDP) Toolbox: mdp module
- Markov Decision Process (MDP) Toolbox: util module
- Markov Decision Process (MDP) Toolbox: example module