Minecraft Diamond Challenge Leaves AI Creators Stuck

5 min read


Minecraft diamond challenge leaves AI creators stumped By Sam Shead Technology reporter



12 December 2019



Most Minecraft players can find the diamonds that are the most important in just a few minutes. However, it's much more difficult to create artificial intelligence that can do this job.
Minecraft Servers



In the summer, Minecraft publisher Microsoft and other companies challenged coders to develop AI agents that could locate the most sought-after gems.



Most people can master it in the first session.



However, none of the more than 660 entries submitted met the challenge.



The results of the MineRL - which is pronounced mineral-related - competition are scheduled to be announced formally on Saturday at the NeurIPS AI conference in Vancouver, Canada.



The objective was to determine if the problem could be solved with a minimum of computing power.



Although there was no winner, one of the organizers said that she was still "hugely amazed by" some of the participants.



Katja Hofmann, principal researcher at Microsoft Research, stated that "the task we set was very difficult." "Finding diamonds in Minecraft takes many steps - from cutting down trees, making tools to exploring caves and actually finding a diamond.



"While no agent has solved the issue completely but they have made a significant amount of progress and have learned to make many of the tools needed along the way."



Mining diamonds



Minecraft has become wildly popular since its release in 2011.



The game's open-world format has been downloaded more than 180 million times and the title is played by more than 112 million players every month.



Diamond is a very important resource in Minecraft. It can be used to make powerful weapons and armour.



To get the precious stone However, the player must follow a number of other steps.



Jules Portelly, a Minecraft player, said that it shouldn't take more then 20 minutes to get your first diamonds if you're familiar playing the game.



The entry requirements were that applicants could only use one graphics processing unit (GPU) and they must complete four days of training. AI systems often require months or even years of gaming time to master games like StarCraft II.



To help them train their systems, a small Minecraft dataset comprising 60 million frames of player data was made available to all participants.



"At the start of every episode they spawned in a procedurally-generated Minecraft world," explained Dr Hofmann.



"So they had to learn the concept about finding resources, making tools, and finding a gem."



Minecraft for artificial intelligence research



DeepMind AI achieves Grandmaster status at Starcraft 2



Minecraft players to be helped by AI assistant



The goal was to have coders create programs that were learned by imitation, a technique called "imitation learning".



This is about trying to get AI agents to adopt the most effective approach by making them mimic the way humans or other software can do to complete a task.



It is in contrast to relying entirely on "reinforcement learning", in which agents are taught to find the best solution through trial and error, but without using the knowledge of previous experiences.



AI for all



Research has proven that reinforcement learning can produce superior results.



DeepMind's AlphaGo Zero program, for instance, beat an earlier effort by the research hub that used reinforcement learning and the analysis of data labelled from human behavior to learn the board game Go.



However, this "pure" method usually requires much more computing power, making it too expensive for researchers other than large organisations or governments.



William Guss, the main organizer of the competition and a PhD student at Carnegie Mellon University, told the BBC that the point of the contest was to demonstrate that "throwing massive compute at problems isn't the best way to push the state of the art in a field".



He added: "It works directly against democratising access to these systems for reinforcement learning and leaves the capacity to train agents in complicated environments to corporations that have vast amounts of computing."



However, the outcome may highlight the advantages these entities with a good financial position have.



Minecraft graphics to look more real



19 August 2019



Minecraft player loses five-year-long game



29 April 2019

In case you have found a mistake in the text, please send a message to the author by selecting the mistake and pressing Ctrl-Enter.
Comments (0)

    No comments yet

You must be logged in to comment.

Sign In / Sign Up