# Expedition & Expansion: Leveraging Semantic Representations for Goal-Directed Exploration in Continuous Cellular Automata

arXiv: https://arxiv.org/abs/2509.03863 · HTML: https://mlsanity.com/paper/2509.03863/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 4 Sep 2025.

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Skew-Fit: State-Covering Self-Supervised Reinforcement Learning](https://mlsanity.com/paper/1903.03698/) (2019)
- [Quality and Diversity Optimization: A Unifying Modular Framework](https://mlsanity.com/paper/1708.09251/) (2017)
- [Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey](https://mlsanity.com/paper/2012.09830/) (2020)
- [Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning](https://mlsanity.com/paper/1708.02190/) (2017)
- [OMNI: Open-endedness via Models of human Notions of Interestingness](https://mlsanity.com/paper/2306.01711/) (2023)
- [Autonomous skill discovery with Quality-Diversity and Unsupervised Descriptors](https://mlsanity.com/paper/1905.11874/) (2019)
- [Semantic Exploration from Language Abstractions and Pretrained Representations](https://mlsanity.com/paper/2204.05080/) (2022)
- [Procedural Content Generation through Quality Diversity](https://mlsanity.com/paper/1907.04053/) (2019)
- [Lenia - Biology of Artificial Life](https://mlsanity.com/paper/1812.05433/) (2018)
- [Scaling MAP-Elites to Deep Neuroevolution](https://mlsanity.com/paper/2003.01825/) (2020)
- [Augmenting Autotelic Agents with Large Language Models](https://mlsanity.com/paper/2305.12487/) (2023)
- [Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration](https://mlsanity.com/paper/1803.00781/) (2018)
- [Automating the Search for Artificial Life with Foundation Models](https://mlsanity.com/paper/2412.17799/) (2024)
- [Intrinsically Motivated Discovery of Diverse Patterns in Self-Organizing Systems](https://mlsanity.com/paper/1908.06663/) (2019)
- [Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems](https://mlsanity.com/paper/2007.01195/) (2020)
- [Toward Artificial Open-Ended Evolution within Lenia using Quality-Diversity](https://mlsanity.com/paper/2406.04235/) (2024)
- [Flow-Lenia: Towards open-ended evolution in cellular automata through mass conservation and parameter localization](https://mlsanity.com/paper/2212.07906/) (2022)
- [Discovering Sensorimotor Agency in Cellular Automata using Diversity Search](https://mlsanity.com/paper/2402.10236/) (2024)
- [Multi-Objective Quality-Diversity for Crystal Structure Prediction](https://mlsanity.com/paper/2403.17164/) (2024)
- [Looking for Complexity at Phase Boundaries in Continuous Cellular Automata](https://mlsanity.com/paper/2402.17848/) (2024)

## Built on by (most cited first, 1 of 1)

- [The Artificial Experimentalist: Discovery and Control of Self-Organizing Phenomena with Autotelic Reinforcement Learning](https://mlsanity.com/paper/2608.26116/) (2026)

## Abstract (arXiv)

Discovering diverse visual patterns in continuous cellular automata (CA) is challenging due to the vastness and redundancy of high-dimensional behavioral spaces. Traditional exploration methods like Novelty Search (NS) expand locally by mutating known novel solutions but often plateau when local novelty is exhausted, failing to reach distant, unexplored regions. We introduce Expedition and Expansion (E&E), a hybrid strategy where exploration alternates between local novelty-driven expansions and goal-directed expeditions. During expeditions, E&E leverages a Vision-Language Model (VLM) to generate linguistic goals--descriptions of interesting but hypothetical patterns that drive exploration toward uncharted regions. By operating in semantic spaces that align with human perception, E&E both evaluates novelty and generates goals in conceptually meaningful ways, enhancing the interpretability and relevance of discovered behaviors. Tested on Flow Lenia, a continuous CA known for its rich, emergent behaviors, E&E consistently uncovers more diverse solutions than existing exploration methods. A genealogical analysis further reveals that solutions originating from expeditions disproportionately influence long-term exploration, unlocking new behavioral niches that serve as stepping stones for subsequent search. These findings highlight E&E's capacity to break through local novelty boundaries and explore behavioral landscapes in human-aligned, interpretable ways, offering a promising template for open-ended exploration in artificial life and beyond.