An Open-Ended Challenge in Simple Complexity, Exploration, and Machine Creativity
Carle’s Game is an open-ended challenge for creative machine intelligence based on the Cellular Automata Reinforcement Learning Environment (CARLE). CARLE is a flexible, fast environment that supports arbitrary Life-like cellular automata (CA) rule sets, and the Carle’s Game challenge is part of the IEEE 2021 Conference on Games. Check out the challenge guidelines in the project README, submit an entry to the challenge by opening an issue and linking to your work, check out the example submissions, join/start a discussion, or just silently check out the project without ever telling anyone you were here.
Posts
Update 2021-07-27: Prediction, Surprise, and Noisy TVs
Update 2021-06-17: Blog update and example submissions.
Update 2021-04-05: Alpha release: support for run-length encoding, stacked reward wrappers, and more.
Update 2021-02-14: Fix cellular birth logic, blog post about evaluation in open-endedness.
Update 2021-01-17: New exploration bonus and RND bug-fixes
Introducing Carle's Game
subscribe via RSS