Carle's Game: An Open-Ended Challenge in Exploratory Machine Creativity

TL;DR

This paper introduces CARLE, a cellular automata simulator and reinforcement learning environment, and presents Carle's Game, a challenge to foster open-ended machine exploration and creativity across diverse automata universes.

Contribution

It presents CARLE, a flexible, fast, and simple cellular automata environment, and introduces Carle's Game as a challenge to advance machine creativity and exploration.

Findings

CARLE can simulate over 262,144 automata rules.

CARLE achieves tens of thousands of steps per second with GPU acceleration.

Provides initial agent policies and algorithms for exploration and learning.

Abstract

This paper is both an introduction and an invitation. It is an introduction to CARLE, a Life-like cellular automata simulator and reinforcement learning environment. It is also an invitation to Carle's Game, a challenge in open-ended machine exploration and creativity. Inducing machine agents to excel at creating interesting patterns across multiple cellular automata universes is a substantial challenge, and approaching this challenge is likely to require contributions from the fields of artificial life, AI, machine learning, and complexity, at multiple levels of interest. Carle's Game is based on machine agent interaction with CARLE, a Cellular Automata Reinforcement Learning Environment. CARLE is flexible, capable of simulating any of the 262,144 different rules defining Life-like cellular automaton universes. CARLE is also fast and can simulate automata universes at a rate of tens of thousands of steps per second through a combination of vectorization and GPU acceleration. Finally, CARLE is simple. Compared to high-fidelity physics simulators and video games designed for human players, CARLE's two-dimensional grid world offers a discrete, deterministic, and atomic universal playground, despite its complexity. In combination with CARLE, Carle's Game offers an initial set of agent policies, learning and meta-learning algorithms, and reward wrappers that can be tailored to encourage exploration or specific tasks.