Alternatives and Inspirations

PyMDPs wouldn't exist if not for the work of many other researchers and engineers in the field of reinforcement learning and decision making. Here are some of the libraries and tools that have inspired PyMDPs and that you might find useful for your own projects.

• POMDPs.jl POMDPs.jl is a Julia package for working with Partially Observable Markov Decision Processes (POMDPs). It provides a flexible and extensible framework for defining POMDPs and solving them using a variety of algorithms. This package was originally developed by Mykel Kochenderfer and collaborators at Stanford University.
• Gynmnasium Gynasium, formerly OpenAI Gym, is a toolkit for developing and comparing reinforcement learning algorithms. It supports teaching agents everything from walking to playing games like Pong or Pinball.