Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training

• URL: http://arxiv.org/abs/2604.11248v1
• Date: Mon, 13 Apr 2026 09:56:22 GMT
• Title: Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training
• Abstract summary: We introduce PBT-NCA, a meta-evolutionary algorithm that evolves a population of Petri Dish Neural Cellular Automata.<n>By actively penalizing monocultures and dead states, PBT-NCA sustains a state of effective complexity that is neither globally ordered nor globally random.
• Score: 46.01525213637453
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The generation of sustained, open-ended complexity from local interactions remains a fundamental challenge in artificial life. Differentiable multi-agent systems, such as Petri Dish Neural Cellular Automata (PD-NCA), exhibit rich self-organization driven purely by spatial competition; however, they are highly sensitive to hyperparameters and frequently collapse into uninteresting patterns and dynamics, such as frozen equilibria or structureless noise. In this paper, we introduce PBT-NCA, a meta-evolutionary algorithm that evolves a population of PD-NCAs subject to a composite objective that rewards both historical behavioral novelty and contemporary visual diversity. Driven by this continuous evolutionary pressure, PBT-NCA spontaneously generates a plethora of emergent lifelike phenomena over extended horizons-a hallmark of true open-endedness. Strikingly, the substrate autonomously discovers diverse morphological survival and self-organization strategies. We observe highly regular, coordinated periodic waves; spore-like scattering where homogeneous groups eject cell-like clusters to colonize distant territories; and fluid, shape-shifting macro-structures that migrate across the substrate, maintaining stable outer boundaries that enclose highly active interiors. By actively penalizing monocultures and dead states, PBT-NCA sustains a state of effective complexity that is neither globally ordered nor globally random, operating persistently at the "edge of chaos".

Related papers

• Many-Body Mobility Edge and Non-Hermitian Skin Effect in an Interacting Quasi-Periodic Spin Chain [0.5096292096000188]
  We study an interacting non-Hermitian spin chain subject to a quasi-periodic longitudinal field.<n>We discover a "D-shaped" many-body mobility edge that separates extended and localized eigenstates.<n>We demonstrate that the skin effect induces multifractal scaling in the non-Hermitian eigenstates, providing a clear signature of the many-body skin effect.
  arXiv  Detail & Related papers  (2026-08-07T10:34:17Z)
• C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift [1.6332363167294173]
  We propose a fully distributed Federated Learning (FL) approach where nodes self-organize into learning groups through spatial clustering.<n>We evaluate our approach on synthetic experiments that systematically reproduce spatial and temporal shifts.
  arXiv  Detail & Related papers  (2026-06-16T14:50:20Z)
• Directing Open-Ended Evolution in Artificial Life via Multi-Scale Path Divergence [0.24214594180459362]
  MSPD (Multi-Scale Path Divergence) is a renormalization-group-inspired scalar.<n>It quantifies the temporal multiscale organization of heterogeneity in local transition laws.<n>MSPD is an explicit formula and plays a dual role: as a gradient-free fitness function and as a post-hoc analytical lens.
  arXiv  Detail & Related papers  (2026-06-12T22:24:12Z)
• When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy [84.66775319652074]
  In RL, diversity is often assumed to correlate with policy entropy, motivating entropy regularization.<n>We show this intuition breaks in flow models: policy entropy remains constant, even while perceptual diversity collapses.<n>We introduce perceptual entropy that captures diversity in a perceptual space and maintains the property of standard entropy.
  arXiv  Detail & Related papers  (2026-05-12T13:29:10Z)
• Online Continual Learning with Dynamic Label Hierarchies [72.33335166136045]
  We introduce a new problem setting, DHOCL, where severity evolve across granularities and each sample provides supervision at a single hierarchical level.<n>In this setting, we find two fundamental issues: (i) partial supervision under mixed granularities provides only point-wise signals over an evolving path-wise hierarchy, which constrains plasticity and undermines cross-level semantic consistency.<n>We propose HALO, which adaptively combines complementary classification heads, regularized by organized learnable hierarchical prototypes, enabling rapid adaptation, hierarchical consistency, and structured knowledge consolidation as the taxonomy evolves.
  arXiv  Detail & Related papers  (2026-05-12T08:20:23Z)
• Foundations of Diffusion Models in General State Spaces: A Self-Contained Introduction [54.95522167029998]
  This article is a self-contained primer on diffusion over general state spaces.<n>We develop the discrete-time view (forward noising via Markov kernels and learned reverse dynamics) alongside its continuous-time limits.<n>A common variational treatment yields the ELBO that underpins standard training losses.
  arXiv  Detail & Related papers  (2025-12-04T18:55:36Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• Identity Increases Stability in Neural Cellular Automata [0.0]
  We present a method for improving the stability of NCA-grown organisms by introducing an 'identity' layer with simple constraints during training.<n>Results show that NCAs grown in close proximity are more stable compared with the original NCA model.<n>This work lays the foundation for further study of the interaction between NCA-grown organisms, paving the way for studying social interaction at a cellular level in artificial organisms.
  arXiv  Detail & Related papers  (2025-08-08T15:18:01Z)
• Flow-Lenia: Emergent evolutionary dynamics in mass conservative continuous cellular automata [17.764206513343684]
  We propose Flow-Lenia, a mass conservative extension of Lenia.<n>We show that Flow-Lenia allows us to embed the parameters of the model, defining the properties of the emerging patterns.<n>We shed light on the emergent evolutionary dynamics taking place in this system.
  arXiv  Detail & Related papers  (2025-06-10T08:37:26Z)
• Whenever, Wherever: Towards Orchestrating Crowd Simulations with Spatio-Temporal Spawn Dynamics [65.72663487116439]
  We propose nTPP-GMM that models spawn-temporal spawn dynamics using Neural Temporal Point Processes.<n>We evaluate our approach by simulations of three diverse real-world datasets with nTPP-GMM.
  arXiv  Detail & Related papers  (2025-03-20T18:46:41Z)
• Emergent Collective Reproduction via Evolving Neuronal Flocks [0.0]
  This study facilitates the understanding of evolutionary transitions in individuality (ETIs) through a novel artificial life framework, named VitaNova. VitaNova intricately merges self-organization and natural selection to simulate the emergence of complex, reproductive groups.
  arXiv  Detail & Related papers  (2024-09-20T06:22:24Z)
• Dynamics of inhomogeneous spin ensembles with all-to-all interactions: breaking permutational invariance [49.1574468325115]
  We investigate the consequences of introducing non-uniform initial conditions in the dynamics of spin ensembles characterized by all-to-all interactions. We find that the dynamics of the spin ensemble now spans a more expansive effective Hilbert space.
  arXiv  Detail & Related papers  (2023-09-19T16:44:14Z)
• Eco-evolutionary Dynamics of Non-episodic Neuroevolution in Large Multi-agent Environments [0.0]
  We present a method for continuously evolving adaptive agents without any environment or population reset. We show that NE can operate in an ecologically non-episodic multi-agent setting, finding sustainable collective foraging strategies.
  arXiv  Detail & Related papers  (2023-02-18T13:57:27Z)
• Flow-Lenia: Towards open-ended evolution in cellular automata through mass conservation and parameter localization [16.11867905890754]
  Flow Lenia enables the integration of the parameters of the CA update rules within the CA dynamics. We show that Flow Lenia enables the integration of the parameters of the CA update rules within the CA dynamics.
  arXiv  Detail & Related papers  (2022-12-14T15:07:21Z)
• Growing Isotropic Neural Cellular Automata [63.91346650159648]
  We argue that the original Growing NCA model has an important limitation: anisotropy of the learned update rule. We demonstrate that cell systems can be trained to grow accurate asymmetrical patterns through either of two methods.
  arXiv  Detail & Related papers  (2022-05-03T11:34:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.