Minecraft Diamond Challenge Leaves AI Creators Stuck

From Science Wiki
Jump to: navigation, search

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



12 December 2019



It takes just a few minutes for new Minecraft players to figure out how to dig up the diamonds that are key to the game, but educating artificial intelligence to do it is more difficult than we expected.



Microsoft, an Minecraft publisher and other companies challenged developers to create AI agents that could find the sought-after treasures.



Most can crack it in their first session.



Of the 660 entries, not one of them was up to the task.



The official announcement of the results of the MineRL competition that is known as "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 a huge amount of computing power.



Despite the lack of any winners One of the organisers said that she was "hugely impressed" by some of the participants.



Katja Hofmann, principal researcher at Microsoft Research, stated that "the task we asked for was very challenging." "Finding diamonds in Minecraft involves a number of steps - from cutting trees, to making tools to exploring caves and actually finding a diamond.



"While no agent has solved the issue completely, they have made a significant amount of progress and have made some of the tools required along the way."



Mining diamonds



Since its release in 2011 Minecraft has been extremely popular.



More than 180 million copies of the game that is open-world have been sold, and the game has more than 112 million monthly active players.



Diamond is one of the most valuable resources in Minecraft because it can be used to create strong armour and powerful weapons. minecraft-servers.website



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



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



The entry requirements for entry were that applicants could only use one graphics processing unit (GPU), and that they undergo four days of instruction. AI systems typically require months or even years of gaming to master games such as StarCraft II.



To help them 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 concept of finding resources, making tools , and finding the diamond."



Minecraft for artificial intelligence research



DeepMind AI achieves Grandmaster status at Starcraft 2



AI assistant to assist Minecraft players



The organizers wanted coders to develop programs that could be learned by imitation, a method known as "imitation learning".



This means trying to convince AI agents to adopt the most efficient method by making them mimic what humans or other programs do to solve a task.



This contrasts with "reinforcement learning", where agents are trained to find the most effective solution by trial and error.



All AI



Research has shown that reinforcement learning can sometimes lead to superior results.



For instance DeepMind's AlphaGo Zero program trumped one of the research hub's earlier initiatives, which employed reinforcement learning and the study of labelled data from human play to help players learn the board game Go.



This "pure" method requires more computing power and is too expensive for researchers who are not employed in large organizations or in government.



William Guss, a Carnegie Mellon University PhD student, was the primary organizer of the competition. He explained that the purpose of the competition was to prove that "throwing massive computation at problems isn't always the right way to push the boundaries of technology as a field."



He added, "It works against democratising access to these reinforcement learning systems and leaves the capacity for agents to learn in complex environments to large corporations with vast computing resources."



But the outcome may be a way to highlight the advantages these well-funded companies have.



Minecraft graphics to appear more real



19 August 2019



A Minecraft player is unable to play for five years.



29 April 2019