Timezone: »
Self-organization of complex morphological patterns from local interactions is a fascinating phenomenon in many natural and artificial systems. In the artificial world, typical examples of such morphogenetic systems are cellular automata. Yet, their mechanisms are often very hard to grasp and so far scientific discoveries of novel patterns have primarily been relying on manual tuning and ad hoc exploratory search. The problem of automated diversity-driven discovery in these systems was recently introduced [26, 62], highlighting that two key ingredients are autonomous exploration and unsupervised representation learning to describe “relevant” degrees of variations in the patterns. In this paper, we motivate the need for what we call Meta-diversity search, arguing that there is not a unique ground truth interesting diversity as it strongly depends on the final observer and its motives. Using a continuous game-of-life system for experiments, we provide empirical evidences that relying on monolithic architectures for the behavioral embedding design tends to bias the final discoveries (both for hand-defined and unsupervisedly-learned features) which are unlikely to be aligned with the interest of a final end-user. To address these issues, we introduce a novel dynamic and modular architecture that enables unsupervised learning of a hierarchy of diverse representations. Combined with intrinsically motivated goal exploration algorithms, we show that this system forms a discovery assistant that can efficiently adapt its diversity search towards preferences of a user using only a very small amount of user feedback.
Author Information
Mayalen Etcheverry (INRIA)
Clément Moulin-Frier (Inria)
Pierre-Yves Oudeyer (INRIA)
Related Events (a corresponding poster, oral, or spotlight)
-
2020 Poster: Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems »
Wed. Dec 9th 05:00 -- 07:00 PM Room Poster Session 3 #777
More from the Same Authors
-
2022 : Using Confounded Data in Offline RL »
Maxime Gasse · Damien GRASSET · Guillaume Gaudron · Pierre-Yves Oudeyer -
2023 Workshop: Agent Learning in Open-Endedness Workshop »
Minqi Jiang · Mikayel Samvelyan · Jack Parker-Holder · Mayalen Etcheverry · Yingchen Xu · Michael Dennis · Roberta Raileanu -
2022 Poster: EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL »
Thomas Carta · Pierre-Yves Oudeyer · Olivier Sigaud · Sylvain Lamprier -
2021 : Grounding an Ecological Theory of Artificial Intelligence in Human Evolution »
Eleni Nisioti · Clément Moulin-Frier -
2021 : Sculpting (human-like) AI systems by sculpting their (social) environments »
Pierre-Yves Oudeyer -
2021 : Grounding an Ecological Theory of Artificial Intelligence in Human Evolution »
Eleni Nisioti · Clément Moulin-Frier -
2021 Poster: Grounding Spatio-Temporal Language with Transformers »
Tristan Karch · Laetitia Teodorescu · Katja Hofmann · Clément Moulin-Frier · Pierre-Yves Oudeyer -
2020 : Panel discussion »
Pierre-Yves Oudeyer · Marc Bellemare · Peter Stone · Matt Botvinick · Susan Murphy · Anusha Nagabandi · Ashley Edwards · Karen Liu · Pieter Abbeel -
2020 : Invited talk: PierreYves Oudeyer "Machines that invent their own problems: Towards open-ended learning of skills" »
Pierre-Yves Oudeyer -
2020 Poster: Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration »
Cédric Colas · Tristan Karch · Nicolas Lair · Jean-Michel Dussoux · Clément Moulin-Frier · Peter F Dominey · Pierre-Yves Oudeyer -
2016 Demonstration: Autonomous exploration, active learning and human guidance with open-source Poppy humanoid robot platform and Explauto library »
Sébastien Forestier · Yoan Mollard · Pierre-Yves Oudeyer -
2012 Poster: Exploration in Model-based Reinforcement Learning by Empirically Estimating Learning Progress »
Manuel Lopes · Tobias Lang · Marc Toussaint · Pierre-Yves Oudeyer