PHYRE is a benchmark for PHYsical REasoning that contains a set of simple classical mechanics puzzles in a 2D environment. The benchmark is designed to encourage development of sample-efficient learning algorithms that generalize well across puzzles.

Benchmark For Physical Reasoning

PHYRE provides a set of physics puzzles in a simulated 2D world. Each puzzle has a goal state (e.g., make the green ball touch the blue ball) and an initial state in which the goal is not satisfied; A puzzle can be solved by placing one or more new bodies in the environment such that when the physical simulation is run the goal is satisfied.

Read more about PHYRE on our Research In Brief blog post.


Get Started


  • Install the package. PHYRE is easiest installed with pip, but a series of different installation methods are provided.

    conda create -n phyre python=3.6 && conda activate phyre
    pip install phyre

  • 2

  • Explore the tasks on the PHYRE player, and check out the tutorials to gain familiarity with the API.

  • 3

  • Use PHYRE as an environment to test existing agents, or start developing new agents to solve PHYRE.

  • More Tools


    House3D is a rich environment containing thousands of 3D scenes of visually realistic houses with full labeling.


    ELF is a platform for game research that allows developers to train and test their algorithms in various game environments.

    Join Us

    Tackle the world's most complex technology challenges

    Join Our Team

    Latest News

    Visit the AI Blog for updates on recent publications, new tools, and more.

    Visit Blog