Notes

Minecraft Diamond Challenge Leaves AI Creators Stuck

Minecraft diamond challenge leaves AI creators baffled by Sam Shead Technology reporter



12 December 2019



It takes just a few minutes for new Minecraft players to work out how to mine the diamonds that are essential to the game, but training artificial intelligence to do this has been more difficult than anticipated.



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



Most can crack it in their first session.



However there was no way to prove that any of the more than 660 entries submitted met the requirements.



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



The goal was to see whether the problem could be solved without requiring a huge amount of computing power.



Despite not having a winner, one organizer said that she was still "hugely amazed by" some of the participants.



"The task we asked for is very hard," said Katja Hofmann who is a principal researcher with Microsoft Research. "Finding a diamond in Minecraft involves a number of steps - from cutting trees, making tools, to exploring caves and actually finding a diamond.



"While no submitted agent is able to solve the task fully but they have made significant progress and learned how to use many of the tools needed."



Mining diamonds



Since its debut in the year 2011, Minecraft has become a hugely popular game.



The open-world game has been downloaded more than 180 million times and the game is played by more than 112,000,000 people each month.
Liberty


Diamond is one of the most important resources found in Minecraft because it can be used to create strong armor and powerful weapons.



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



Jules Portelly, a Minecraft player, said it shouldn't take more than 20 minutes to get your first diamonds if you're comfortable with the game.



The entry requirements were that participants could only utilize one graphics processing unit (GPU) and they must complete four days of training. AI systems usually require months or even years of gaming to master games such as StarCraft II.



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



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



"So they really needed to understand the idea of locating resources, making tools , and finding a diamond."



Minecraft for artificial intelligence experiments



DeepMind AI achieves Grandmaster status at Starcraft 2



AI assistant to aid Minecraft players



The developers were asked to create programs that were learned through imitation, a technique called "imitation learning".



This involves trying to convince AI agents to adopt the most effective approach by allowing them to emulate the way humans or other software can do to complete a task.



This is in contrast to "reinforcement learning" in which agents are trained to determine the best solution through trial and error.



AI for all



Researchers have discovered that using reinforcement learning by itself can lead to better results.



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



This "pure" method requires more computing power, and is too costly for researchers not working in large companies or governments.



William Guss, the main contest's organiser and 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".



He said, "It works against democratising access to these systems of reinforcement learning and leaves the capacity for agents to learn in complex environments to companies that have vast areas of computing."



However, the outcome may help to highlight the advantages these well-funded organizations have.



Minecraft graphics to be more 'realistic'



19 August 2019



A Minecraft player is not able to play for five years.



29 April 2019


Website: https://libertycm.tv/