2000 character limit reached
Quality Diversity in the Amorphous Fortress (QD-AF): Evolving for Complexity in 0-Player Games
Published 4 Dec 2023 in cs.AI and cs.MA | (2312.02231v1)
Abstract: We explore the generation of diverse environments using the Amorphous Fortress (AF) simulation framework. AF defines a set of Finite State Machine (FSM) nodes and edges that can be recombined to control the behavior of agents in the `fortress' grid-world. The behaviors and conditions of the agents within the framework are designed to capture the common building blocks of multi-agent artificial life and reinforcement learning environments. Using quality diversity evolutionary search, we generate diverse sets of environments. These environments exhibit certain types of complexity according to measures of agents' FSM architectures and activations, and collective behaviors. Our approach, Quality Diversity in Amorphous Fortress (QD-AF) generates families of 0-player games akin to simplistic ecological models, and we identify the emergence of both competitive and co-operative multi-agent and multi-species survival dynamics. We argue that these generated worlds can collectively serve as training and testing grounds for learning algorithms.
- Emergent tool use from multi-agent autocurricula. arXiv preprint arXiv:1909.07528 (2019).
- Christopher Bamford. 2021. Griddly: A platform for AI research in games. Software Impacts 8 (2021), 100066.
- GriddlyJS: A Web IDE for Reinforcement Learning. Advances in Neural Information Processing Systems 35 (2022), 15051–15065.
- Emergent Complexity via Multi-Agent Competition. In International Conference on Learning Representations.
- Open problems in artificial life. Artificial life 6, 4 (2000), 363–376.
- Procedural content generation using neuroevolution and novelty search for diverse video game levels. In Proceedings of the Genetic and Evolutionary Computation Conference. 1028–1037.
- Staffan Björk and Jesper Juul. 2012. Zero-player games or: what we talk about when we talk about players. In Philosophy of Computer Games Conference, Madrid.
- Amorphous Fortress: Observing Emergent Behavior in Multi-Agent FSMs. arXiv preprint arXiv:2306.13169 (2023).
- Say “sul sul!” to simsim, a sims-inspired platform for sandbox game ai. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, Vol. 16. 182–188.
- Emergent complexity and zero-shot transfer via unsupervised environment design. Advances in neural information processing systems 33 (2020), 13049–13061.
- Manoj Deshpande and Brian Magerko. 2021. Drawcto: A Multi-Agent Co-Creative AI for Collaborative Non-Representational Art. (2021).
- Novelty search: a theoretical perspective. In Proceedings of the Genetic and Evolutionary Computation Conference. 99–106.
- Sam Earle. 2020. Using fractal neural networks to play simcity 1 and conway’s game of life at variable scales. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (2020).
- Illuminating diverse neural cellular automata for level generation. In Proceedings of the Genetic and Evolutionary Computation Conference. 68–76.
- Video games as a testbed for open-ended phenomena. In 2021 IEEE Conference on Games (CoG). IEEE, 1–9.
- Minedojo: Building open-ended embodied agents with internet-scale knowledge. Advances in Neural Information Processing Systems 35 (2022), 18343–18362.
- Brax-A Differentiable Physics Engine for Large Scale Rigid Body Simulation. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1).
- Measuring and optimizing behavioral complexity for evolutionary reinforcement learning. In International Conference on Artificial Neural Networks. Springer, 765–774.
- Evocraft: A new challenge for open-endedness. In Applications of Evolutionary Computation: 24th International Conference, EvoApplications 2021, Held as Part of EvoStar 2021, Virtual Event, April 7–9, 2021, Proceedings 24. Springer, 325–340.
- Exploring open-ended gameplay features with Micro RollerCoaster Tycoon. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (2021).
- Cristina Guerrero-Romero and Diego Perez-Liebana. 2021. Map-elites to generate a team of agents that elicits diverse automated gameplay. In 2021 IEEE Conference on Games (CoG). IEEE, 1–8.
- Nicholas Guttenberg and LB Soros. 2023. Designing Emergence in Games. In ALIFE 2023: Ghost in the Machine: Proceedings of the 2023 Artificial Life Conference. MIT Press.
- Prioritized level replay. In International Conference on Machine Learning. PMLR, 4940–4950.
- Pcgrl: Procedural content generation via reinforcement learning. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, Vol. 16. 95–101.
- Robert Tjarko Lange. 2023. evosax: Jax-based evolution strategies. In Proceedings of the Companion Conference on Genetic and Evolutionary Computation. 659–662.
- Stephen Lavelle. 2013. Puzzlescript. https://www.puzzlescript.net/. Accessed: 2023-12-03.
- Multi-agent actor-critic for mixed cooperative-competitive environments. Advances in neural information processing systems 30 (2017).
- Alexandre Santos Melotti and Carlos Henrique Valerio de Moraes. 2018. Evolving roguelike dungeons with deluged novelty search local competition. IEEE Transactions on Games 11, 2 (2018), 173–182.
- Jean-Baptiste Mouret and Jeff Clune. 2015. Illuminating search spaces by mapping elites. arXiv preprint arXiv:1504.04909 (2015).
- Open-ended search for environments and adapted agents using map-elites. In International Conference on the Applications of Evolutionary Computation (Part of EvoStar). Springer, 651–666.
- Evolving curricula with regret-based environment design. In International Conference on Machine Learning. PMLR, 17473–17498.
- Thomas Pierrot and Arthur Flajolet. 2023. Evolving Populations of Diverse RL Agents with MAP-Elites. arXiv preprint arXiv:2303.12803 (2023).
- Stuart J Russell and Peter Norvig. 2010. Artificial intelligence a modern approach. London.
- MAESTRO: Open-ended environment design for multi-agent reinforcement learning. arXiv preprint arXiv:2303.03376 (2023).
- Tom Schaul. 2013. A video game description language for model-based or interactive learning. In 2013 IEEE Conference on Computational Inteligence in Games (CIG). IEEE, 1–8.
- Picbreeder: evolving pictures collaboratively online. In Proceedings of the SIGCHI conference on human factors in computing systems. 1759–1768.
- Open-endedness: The last grand challenge you’ve never heard of. While open-endedness could be a force for discovering intelligence, it could also be a component of AI itself (2017).
- The neural mmo platform for massively multiagent research. arXiv preprint arXiv:2110.07594 (2021).
- Growing 3d artefacts and functional machines with neural cellular automata. In Artificial Life Conference Proceedings 33, Vol. 2021. MIT Press One Rogers Street, Cambridge, MA 02142-1209, USA journals-info …, 108.
- Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291 (2023).
- Enhanced POET: open-ended reinforcement learning through unbounded invention of learning challenges and their solutions. In Proceedings of the 37th International Conference on Machine Learning. 9940–9951.
- OMNI: Open-endedness via Models of human Notions of Interestingness. arXiv preprint arXiv:2306.01711 (2023).
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.