Skip navigation
Excited to share with Inria Flowers team ADTool, an open-source Python toolkit using…
0:00 / 2:03

Excited to share with Inria Flowers team ADTool, an open-source Python toolkit using…

Inria Flowers team

@FlowersINRIA1.7K followers

Visit on X
111 likesDownloadOriginal post

13,752 views

Excited to share with Inria Flowers team ADTool, an open-source Python toolkit using curiosity-driven AI to explore behavior diversity of complex systems (cellular automata, physics models, ...)!🐍 Serving off-the-shelf strategies like IMGEP You said IMGEP? 👇

10 Comments

Comments from the original post on X (Twitter)

  • Inria Flowers team's profile picture

    @FlowersINRIA

    Intrinsically Motivated Goal Exploration Processes are a family of diversity search algorithms, first developed to model curiosity-driven exploration in humans (like autotelic exploration, where an agent samples its own goals in an open-ended exploration and discovery loop) 2/10

    3 likes

  • Inria Flowers team's profile picture

    @FlowersINRIA

    Schematically during the i'th discovery loop, IMGEP will: -define by itself a new goal g_i -sample p_i trying to have system's response S(p_i) as close as g_i -compute S(p_i) -store (p_i, S(p_i)) to improve future predictions of the parameters required to reach a given goal 3/10

    3 likes

  • Inria Flowers team's profile picture

    @FlowersINRIA

    Such algorithms can be highly relevant for exploring parameterized complex systems, where system behaviors are diverse, mapping with input parameters is non-trivial, and interesting parameters over the set of possible parameters are difficult to find by random search. 4/10

    3 likes

  • Inria Flowers team's profile picture

    @FlowersINRIA

    In particular IMGEP has recently been shown to be very effective in discovering new behaviors in Biological Networks (e.g. GRNs) 🧬 when exploring possible external perturbations. 5/10

    5 likes

  • Inria Flowers team's profile picture

    @FlowersINRIA

    ADTool's modular architecture makes it easy to add your own system, parameter space and observed behavior space, so you can launch your own new discovery processes. 6/10

    3 likes

  • Inria Flowers team's profile picture

    @FlowersINRIA

    Explorations can be launched by command line, and discoveries are organized on disk for easy saving, manipulation, sharing and reloading from past discoveries. 7/10

    3 likes

  • Inria Flowers team's profile picture

    @FlowersINRIA

    Several examples are provided to illustrate the diversity of possible applications, ranging from cellular automata to physics simulation engines and more to come! 8/10

    5 likes

  • Inria Flowers team's profile picture

    @FlowersINRIA

    ADTool also incorporates an interactive visualization aid, so you can see the arrival of discoveries in real time 9/10

    4 likes

  • Inria Flowers team's profile picture

    @FlowersINRIA

    Join the associated Discord to exchange ideas, questions, bugs and share your discoveries, with already some original ones on a class of continuous reversible cellular automata :) 10/10

    3 likes

  • Inria Flowers team's profile picture

    @FlowersINRIA

    @BertChakovsky @randazzoettore @eyvindn @zzznah @nataliemaphd @ThomasCabaret84 @mayalen_etc @forestier_seb @jesselinsane

    5 likes