Post-doctoral research visit f - m exploring self-organizing cellular automata with autotelic exploration algorithms augmented with large vision-language models h/f

A propos d'Inria

Inria est l'institut national de recherche dédié aux sciences et technologies du numérique. Il emploie 2600 personnes. Ses 215 équipes-projets agiles, en général communes avec des partenaires académiques, impliquent plus de 3900 scientifiques pour relever les défis du numérique, souvent à l'interface d'autres disciplines. L'institut fait appel à de nombreux talents dans plus d'une quarantaine de métiers différents. 900 personnels d'appui à la recherche et à l'innovation contribuent à faire émerger et grandir des projets scientifiques ou entrepreneuriaux qui impactent le monde. Inria travaille avec de nombreuses entreprises et a accompagné la création de plus de 200 start-up. L'institut s'eorce ainsi de répondre aux enjeux de la transformation numérique de la science, de la société et de l'économie. Post-Doctoral Research Visit F/M Exploring self-organizing cellular automata with autotelic exploration algorithms augmented with large vision-language models

Télécharger l'offre au format PDF

Le descriptif de l'offre ci-dessous est en Anglais

Type de contrat :
CDD

Niveau de diplôme exigé :
Thèse ou équivalent

Fonction :
Post-Doctorant

Mission confiée

Context :

Many systems that we encounter in nature are self-organized and dynamic, and their study often reveals the emergence of highly-structured morphologies capable of complex behaviors evolved for survival in their environment. In the artificial world, cellular automata (CAs) are among the examples of widely-studied self-organizing systems. For instance, the artificial life (ALife) community has studied the emergence of spatially localized patterns (SLPs) in CAs, giving hints to the theories of the origins of life [1]. SLPs have a local extension and can exist independently of other patterns, resembling artificial "creatures" that can survive for an extended period of time and interact with their environment.

In this project, we will consider Lenia [2,3, 7] as an environment of study. Lenia is a system of continuous cellular automata which can generate a wide range of complex patterns and dynamics, where some of the emerging structures seem to look and behave like real-world microscopic organisms.

While the notions of agents, environment, and possible agent-environment interactions are typically predefined in reinforcement learning and robotic settings; in self-organizing systems such as Lenia the notion of agent and actions (sensorimotor capabilities) is more difficult to interpret. Yet, when looking at the emergent creatures (see example video here and here), they already seem to have some sort of proto-sensorimotor control in their emergent behaviors.

Moreover, our research team has recently proposed a new method for discovering creatures displaying sensorimotor capabilities in cellular automata [9]. For this aim, we have introduced environmental elements in Lenia to search for self-organizing creatures capable of reacting to the perturbations induced by the environment. The method is based on curriculum learning, Intrinsically Motivated Goal Exploration Processes (IMGEP) and on gradient descent. Using a newly-introduced differentiable version of Lenia, the method is able to discover the rules leading to the emergence of robust creatures with sensorimotor capabilities. The creatures obtained, using only local update rules, are able to regenerate and preserve their integrity and structure while dealing with the obstacles or other creatures in their way. They also show great generalization to unseen environments.

However, the current understanding of self-organization processes, and the range of possible self-organized structures, are still limited so far. Furthermore, autotelic exploration algorithms we have used are still limited in terms of the level of abstraction of the goals they consider.

Objective :

The objective of the project will BE to study the use of new kinds of autotelic systems, leveraging large vision-language models, to explore richer and more abstract self-organized patterns in continuous cellular automata. In particular, we will extend algorithms we introduced in [8], enabling them to access the visual modality, enabling automatic learning of high-level linguistic descriptors about self-organized structures. The project will first consist in designing and implementing the new system, leveraging existing large vision-language models. Then, we will conduct various experimental campaign to evaluate both the exploration process and the discovered self-organized structures. An emphasis will BE put on the ability for a human user (which could BE a scientist or an artist) to drive the exploration of the system in directions of interest for him/her, leveraging approaches in [5].

Reference :

[1] Randall D Beer. Autopoiesis and cognition in the game of life. Artificial Life (2004).

[2] Bert Wang-Chak Chan. Lenia-biology of artificial life. Complex Systems (2019).

[3] Bert Wang-Chak Chan. Lenia and expanded universe. Artificial Life (2020). https://www.mitpressjournals.org/doi/abs/10.1162/isal_a_00297

[4] Chris Reinke, Mayalen Etcheverry and Pierre-Yves Oudeyer. Intrinsically Motivated Discovery of Diverse Patterns in Self-Organizing Systems. ICLR (2020). Blogpost : https://developmentalsystems.org/intrinsically_motivated_discovery_of_diverse_patterns

[5] Mayalen Etcheverry, Clément Moulin-Frier and Pierre-Yves Oudeyer. Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems. NeurIPS (2020).

[6] Gautier Hamon, Mayalen Etcheverry, Bert Chan, Clément Moulin-Frier, Pierre-Yves Oudeyer (2021). Learning Sensorimotor Agency in Cellular Automata. Blog post available at https://developmentalsystems.org/sensorimotor-lenia/

[7] Plantec, E., Hamon, G., Etcheverry, M., Oudeyer, P. Y., Moulin-Frier, C., & Chan, B. W. C. (2023, July). Flow-Lenia : Towards open-ended evolution in cellular automata through mass conservation and parameter localization. In ALIFE 2023 : Ghost in the Machine : Proceedings of the 2023 Artificial Life Conference. MIT Press. https://sites.google.com/view/flowlenia/

[8] Colas, C., Teodorescu, L., Oudeyer, P. Y., Yuan, X., & Côté, M. A. (2023). Augmenting Autotelic Agents with Large Language Models. arXiv preprint arXiv :23.

Principales activités

See above

Avantages
- Subsidized meals
- Partial reimbursement of public transport costs
- Possibility of teleworking and flexible organization of working hours
- Professional equipment available (videoconferencing, loan of computer equipment, etc.)
- Social, cultural and sports events and activities
- Access to vocational training
- Social security coverage

Rémunération

2788€ / month (before taxs)