{"slug": "the-artificial-experimentalist-discovery-and-control-of-self-organizing-with", "title": "The Artificial Experimentalist: Discovery and Control of Self-Organizing Phenomena with Autotelic Reinforcement Learning", "summary": "Researchers introduced CARL, an autotelic reinforcement learning agent that discovers and controls self-organizing phenomena in Lenia, a continuous cellular automaton, through closed-loop interventions. CARL found stable solitons across a wide range of Lenia update rules at a higher rate than heuristic baselines, steered existing solitons' movement with few interventions, and enabled humans to guide solitons through mazes in real time via high-level commands. The agents generalized zero-shot to out-of-distribution conditions, suggesting a path toward artificial experimentalist agents for complex systems.", "body_md": "arXiv:2608.26116v1 Announce Type: new\nAbstract: Existing methods for exploring cellular automata and other complex systems mostly operate in open loop: they set initial conditions, execute a full simulation, and observe the outcome, without intervening during execution. We introduce a closed-loop framework based on autotelic reinforcement learning, in which an agent autonomously samples diverse goals and learns a goal-conditioned policy to intervene in a complex system through minimal, local perturbations. We instantiate this framework on Lenia, a continuous cellular automaton known for life-like self-organizing patterns, in an agentic system we call CARL, and demonstrate three capabilities. First, CARL discovers stable solitons across a wide range of Lenia update rules at a higher rate than heuristic baselines. Second, it learns to steer the movement direction of existing solitons with few interventions, showing that CARL can control self-organizing patterns, not only create them. Third, humans can use trained agents to guide solitons through maze environments in real time by specifying high-level directional commands that the agent translates into low-level interventions. Trained across diverse goals, update rules, and random initial states, the agents acquire policies that generalize zero-shot to various out-of-distribution conditions. These results suggest a path toward artificial experimentalist agents that, autonomously or with human guidance, discover and control emergent phenomena in complex systems.", "url": "https://wpnews.pro/news/the-artificial-experimentalist-discovery-and-control-of-self-organizing-with", "canonical_source": "https://arxiv.org/abs/2608.26116", "published_at": "2026-08-28 04:00:00+00:00", "updated_at": "2026-08-28 04:18:43.702449+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-research", "ai-agents"], "entities": ["CARL", "Lenia"], "alternates": {"html": "https://wpnews.pro/news/the-artificial-experimentalist-discovery-and-control-of-self-organizing-with", "markdown": "https://wpnews.pro/news/the-artificial-experimentalist-discovery-and-control-of-self-organizing-with.md", "text": "https://wpnews.pro/news/the-artificial-experimentalist-discovery-and-control-of-self-organizing-with.txt", "jsonld": "https://wpnews.pro/news/the-artificial-experimentalist-discovery-and-control-of-self-organizing-with.jsonld"}}