To share news and perspectives, I am now mostly using LinkedIn: linkedin.com/in/pierreyvesou…
1
1
7
1,993
Introducing the Artificial Experimentalist: an autotelic RL AI scientist that learns to iteratively build and control a diversity of self-organizing solitons in Lenia (and can be applied to any other complex system)! cc @BertChakovsky @hardmaru @kenneth0stanley @okw @jeffclune
🧵 New paper: RL for discovering and controlling self-organizing phenomena. We introduce CARL, a closed-loop agent that learns to create self-organizing patterns in Lenia, steer their behavior, and let humans guide them in real time. Project website + interactive demos below ↓
2
1
49
2,981
Pierre-Yves Oudeyer retweeted
🧵 New paper: RL for discovering and controlling self-organizing phenomena. We introduce CARL, a closed-loop agent that learns to create self-organizing patterns in Lenia, steer their behavior, and let humans guide them in real time. Project website + interactive demos below ↓
11
56
289
28,743
Pierre-Yves Oudeyer retweeted
Brilliant @marko_cvjetko at #ALIFE2026 on "The Artificial Experimentalist: Discovery and Control of Self-Organizing Phenomena with Autotelic Reinforcement Learning"; work with with @drmichaellevin, C. Moulin-Frier, and @pyoudeyer, hal.science/hal-05698778/
2
17
632
I'm happy to share a new podcast where I explain how I got to study curiosity, why it's fundamental in child development and how this got applied in self-improving robots/AI! 🙏 Thanks to the amazing @Choose2BCurious for hosting the podcast ! lynnborton.com/2026/08/27/ma…
2
13
682
Major new results on the impact of AI-driven personalization in MIA Seconde, an #edtech software now used nationwide in French high schools (maths and French)!
2
3
817
[4] Clément, B., Sauzéon, H., Roy, D., & Oudeyer, P. Y. (2024). Improved performances and motivation in intelligent tutoring systems: Combining machine learning and learner choice. arXiv preprint arXiv:2402.01669. arxiv.org/abs/2402.01669
1
161