EvoCraft: A New Challenge for Open-Endedness

Abstract

This paper introduces EvoCraft, a framework for Minecraft designed to study open-ended algorithms. We introduce an API that provides an open-source Python interface for communicating with Minecraft to place and track blocks. In contrast to previous work in Minecraft that focused on learning to play the game, the grand challenge we pose here is to automatically search for increasingly complex artifacts in an open-ended fashion. Compared to other environments used to study open-endedness, Minecraft allows the construction of almost any kind of structure, including actuated machines with circuits and mechanical components. We present initial baseline results in evolving simple Minecraft creations through both interactive and automated evolution. While evolution succeeds when tasked to grow a structure towards a specific target, it is unable to find a solution when rewarded for creating a simple machine that moves. Thus, EvoCraft offers a challenging new environment for automated search methods (such as evolution) to find complex artifacts that we hope will spur the development of more open-ended algorithms. A Python implementation of the EvoCraft framework is available at: github.com/real-itu/Evocraft-py.

Growing 3D Artefacts and Functional Machines with Neural Cellular Automata

“…To interact with Minecraft, we use the EvoCraft API (Grbic et al, 2020). EvoCraft includes a Python programmable interface that allows reading and writing blocks.…”

“…The unique interactions between the blocks provides ways for the Minecraft world to be dynamic independent of the rules of the cellular automaton operating beyond. For the full list of supported blocks consult (Grbic et al, 2020) appendix.…”

The AI Settlement Generation Challenge in Minecraft

“…For example, there is a reinforcement learning focused competition for Minecraft Bots [17,10], and it might be interesting to see if they could operate in procedural generated settlements. Similarly, there is now a framework for using evolutionary algorithms to build machines in Minecraft [8], and it might be worthwhile to see if that framework could be used for our purposes. We are also currently looking at either using additional or new frameworks, beyond the MCEdit [30] and Java Mod based-approaches that we embrace at the moment.…”

“…I'd be very curious to see that! B.11 Ruck Thawonmas, Advisory Member of Team ICE JIT Generator submitted in 2020 competition: ICE-JIT 8 1 : Two points that I found good or was surprised are subterranean utilization and building interiors. They are described below in the following.…”

“…The approach we chose can instead be likened with efforts to create open-ended [25,8] agent behavior in artificial intelligence. As far as we are aware, all existing open-ended AI research is concerned with the behavior of agents in an environment; this competition is an attempt to bring the open-ended mindset to creating generators of environments.…”