Projective Simulation

Agency • Learning • Physics

Get started \| Documentation \| Tutorials

Projective Simulation (PS) is a framework for studying agency from a physical perspective. PS agents learn from interaction with their environment and base their decisions on episodic memory. Internally, their deliberation corresponds to random walks on a clip network (graph), which provides an interpretable route to physical realizations and analysis.

This library all the necessary tools to develop, deploy and train PS agents in a variety of environments. Its content spans from entry-level tutorials that introduce the core principles of PS to cutting-edge research on the latest developments and applications. It is actively developed by the QIC group at UIBK.

Installation

Projective simulation is available for python>=3.10 via

pip install projective_simulation

This will also install the necessary library requirements.

Getting Started

To begin exploring Projective Simulation, we recommend to start with the tutorials, which contain from the basics to more advance applications.

If you want to develop or deploy PS agents, please check the documetation.

Citing

If you found this package useful and used it in your projects, you can either the particular PS paper that you found most useful (see a list here) or use the following to cite the whole library:

here will be some zenodo link