Minecraft Diamond Challenge Leaves AI Creators Stumped

From Valentino Fans
Jump to: navigation, search

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



12 December 2019



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



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



Most people can master it in their first session.



But out of more than 660 entries, not one was up to the task.



The official announcement of the results of the MineRL competition, which is pronounced "mineral", will be made at the NeurIPSAI conference in Vancouver, Canada on Saturday.



The aim had been to determine if the issue could be solved without requiring massive amounts of computing power.



Even though there was no winner, one of the organizers stated that she was "hugely impressed by" some of the participants.



"The task we set out to solve is extremely difficult," said Katja Hofmann who is a principal researcher at Microsoft Research. "Finding a Minecraft diamond involves a number of steps, from cutting trees to making tools to searching caves to finally finding a gem.



"While the submitted agents aren't able to solve the task fully, they have made significant progress and have learned how to utilize many of the tools necessary."



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 game is played by more than 112,000,000 people every month.



Diamond is among the most valuable resources in Minecraft as it can be used to build strong armor and powerful weapons.



To acquire the precious gem However, the player must complete several other steps.



"If you're familiar with the game it shouldn't take you more than 20 minutes to earn your first diamonds," Minecraft player Jules Portelly told the BBC.



Participants were limited to make use of a single graphics processing unit (GPU) and four days of time to train. To put it in perspective, AI systems usually need months or years of game play to master games such as StarCraft II.



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



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



"So they had to master the idea of finding resources, making tools and then finding a gem."



Minecraft to run artificial intelligence tests



DeepMind AI earns Grandmaster status at Starcraft 2



AI assistant to assist Minecraft players



The organizers wanted coders to create programs that were learned by imitation, a method known as "imitation learning".



This means trying to convince AI agents to adopt the most effective approach by allowing them to emulate what humans or other software perform to solve a problem.



This contrasts with "reinforcement learning" where an agent is trained to find the most effective solution through trial and trial and.



All AI



Research has shown that reinforcement learning may result in better results.



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



This "pure" method requires more computing power, and is expensive for researchers who are not working in large companies 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 competition had been to demonstrate that "throwing massive computing at problems isn't always the right way for us to push the limits of the art as a field". Minecraft servers



He said, "It works against democratising access to these systems of reinforcement learning, and leaves the ability to train agents in complex environments to companies that have swathes to compute."



However, the outcome may be a way to highlight the advantages these well-funded organizations have.



Minecraft graphics that look more real



19 August 2019



Minecraft player loses five years of game



29 April 2019