EvoCraft: A New Challenge for Open-Endedness

• URL: http://arxiv.org/abs/2012.04751v1
• Date: Tue, 8 Dec 2020 21:36:18 GMT
• Title: EvoCraft: A New Challenge for Open-Endedness
• Authors: Djordje Grbic, Rasmus Berg Palm, Elias Najarro, Claire Glanois, Sebastian Risi
• Abstract summary: EvoCraft is a framework for Minecraft designed to study open-ended algorithms. EvoCraft offers a challenging new environment for automated search methods (such as evolution) to find complex artifacts.
• Score: 7.927206441149002
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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: https://github.com/real-itu/Evocraft-py.

Related papers

• MineStudio: A Streamlined Package for Minecraft AI Agent Development [12.327116914644627]
  Minecraft has emerged as a valuable testbed for embodied intelligence and sequential decision-making research. This paper presents MineStudio, an open-source software package designed to streamline embodied policy development in Minecraft.
  arXiv  Detail & Related papers  (2024-12-24T09:01:43Z)
• Craftium: An Extensible Framework for Creating Reinforcement Learning Environments [0.5461938536945723]
  This paper presents Craftium, a novel framework for exploring and creating rich 3D visual RL environments. Craftium builds upon the Minetest game engine and the popular Gymnasium API.
  arXiv  Detail & Related papers  (2024-07-04T14:38:02Z)
• Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning [4.067733179628694]
  Craftax is a ground-up rewrite of Crafter in JAX that runs up to 250x faster than the Python-native original. A run of PPO using 1 billion environment interactions finishes in under an hour using only a single GPU. We show that existing methods including global and episodic exploration, as well as unsupervised environment design fail to make material progress on the benchmark.
  arXiv  Detail & Related papers  (2024-02-26T18:19:07Z)
• Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft [88.80684763462384]
  This paper introduces an advanced learning system, named Auto MC-Reward, that leverages Large Language Models (LLMs) to automatically design dense reward functions. Experiments demonstrate a significant improvement in the success rate and learning efficiency of our agents in complex tasks in Minecraft.
  arXiv  Detail & Related papers  (2023-12-14T18:58:12Z)
• Meta-Diversity Search in Complex Systems, A Recipe for Artificial Open-Endedness ? [0.0]
  This article presents what we believe to be some working ingredients for the endless generation of novel increasingly complex artifacts in Minecraft. We simulate an artificial "chemistry" system based on Lenia continuous cellular automaton for generating artifacts, as well as an artificial "discovery assistant" (called Holmes) for the artifact-discovery process.
  arXiv  Detail & Related papers  (2023-12-01T09:40:27Z)
• Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory [97.87093169454431]
  Ghost in the Minecraft (GITM) is a novel framework that integrates Large Language Models (LLMs) with text-based knowledge and memory. We develop a set of structured actions and leverage LLMs to generate action plans for the agents to execute. The resulting LLM-based agent markedly surpasses previous methods, achieving a remarkable improvement of +47.5% in success rate.
  arXiv  Detail & Related papers  (2023-05-25T17:59:49Z)
• Evolving Flying Machines in Minecraft Using Quality Diversity [62.997667081978825]
  EvoCraft is an API for generating structures in Minecraft. This paper applies fitness-based evolution and quality-based diversity search in order to evolve flying machines.
  arXiv  Detail & Related papers  (2023-02-01T22:25:28Z)
• MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge [70.47759528596711]
  We introduce MineDojo, a new framework built on the popular Minecraft game. We propose a novel agent learning algorithm that leverages large pre-trained video-language models as a learned reward function. Our agent is able to solve a variety of open-ended tasks specified in free-form language without any manually designed dense shaping reward.
  arXiv  Detail & Related papers  (2022-06-17T15:53:05Z)
• World-GAN: a Generative Model for Minecraft Worlds [27.221938979891384]
  This work introduces World-GAN, the first method to perform data-driven Procedural Content Generation via Machine Learning in Minecraft. Based on a 3D Generative Adversarial Network (GAN) architecture, we are able to create arbitrarily sized world snippets from a given sample.
  arXiv  Detail & Related papers  (2021-06-18T14:45:39Z)
• Scaling Imitation Learning in Minecraft [114.6964571273486]
  We apply imitation learning to attain state-of-the-art performance on hard exploration problems in the Minecraft environment. An early version of our approach reached second place in the MineRL competition at NeurIPS 2019.
  arXiv  Detail & Related papers  (2020-07-06T12:47:01Z)
• AutoML-Zero: Evolving Machine Learning Algorithms From Scratch [76.83052807776276]
  We show that it is possible to automatically discover complete machine learning algorithms just using basic mathematical operations as building blocks. We demonstrate this by introducing a novel framework that significantly reduces human bias through a generic search space. We believe these preliminary successes in discovering machine learning algorithms from scratch indicate a promising new direction in the field.
  arXiv  Detail & Related papers  (2020-03-06T19:00:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.