MineDojo: A Framework for Building Generalized Autonomous Agents
MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
We introduce minedojo, a new framework built on the popular minecraft game that features a simulation suite with thousands of diverse open-ended tasks and an internet-scale knowledge base with minecraft videos, tutorials, wiki pages, and forum discussions.
Using minedojo s data, 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 shapingreward.