Welcome to pymdp’s documentation!

pymdp is a Python package for simulating active inference agents in discrete space and time, using partially-observed Markov Decision Processes (POMDPs) as a generative model class. The package is designed to be modular and flexible, to enable users to design and simulate bespoke active inference models with varying levels of specificity to a given task.

For a theoretical overview of active inference and the motivations for developing this package, please see our companion paper: “pymdp: A Python library for active inference in discrete state spaces”.

Installation & Usage

• Installation
• pymdp Fundamentals
• Tutorial 1: Active inference from scratch
• Tutorial 2: the Agent API

Examples

• Active Inference Demo: T-Maze Environment
• Active Inference Demo: Epistemic Chaining

Modules

• Inference
• Control
• Learning
• Algos
  • Sub-libraries

Agent and environment API

• Agent class
• Env
  • Base class
  • Specific environment implementations

Additional learning materials

• Computing the variational free energy in categorical models

Indices and tables

• Index

• Module Index

• Search Page