CARL: RL agent learns to create and steer self-organizing Lenia patterns
danbri · x · 2026-09-19
New paper CARL introduces a closed-loop RL agent that learns to create self-organizing patterns in Lenia, steer their behavior, and let humans guide them in real time. Project website includes interactive demos.
Commentators call it a milestone: RL can now actively control self-organizing patterns toward goals. Combined with NCA+IMGEP and perceptual occlusion as passive controls, the field now has a diverse toolbox for steering self-organizing phenomena.
More from Research
- USRA details NASA-IBM lunar foundation model fusing 11 lunar data modalities — victormustar · 2026-09-19
- NASA and IBM open-source lunar foundation model pretrained on 2M multimodal tiles — victormustar · 2026-09-19
- Stabilizing RL with a simple second-year probability trick: the covariance identity — PMinervini · 2026-09-19
- willcb: in-context learning for personal continual learning needs neurosymbolic harnesses — willcb · 2026-09-19
- Online RL via task flywheels from live interaction traces is what actually works today — willcb · 2026-09-19
- Tobi Lütke sparks debate: why discriminative models can't be universal classifiers — caglar_ee · 2026-09-19