{"id":388346,"date":"2017-06-05T06:00:25","date_gmt":"2017-06-05T13:00:25","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?p=388346"},"modified":"2017-06-05T12:38:37","modified_gmt":"2017-06-05T19:38:37","slug":"malmo-collaborative-ai-challenge-winners","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/en-us\/research\/blog\/malmo-collaborative-ai-challenge-winners\/","title":{"rendered":"Presenting the winners of the Project Malmo Collaborative AI Challenge"},"content":{"rendered":"

By Noburu Kuno, Senior Research Program Manager; Scarlet Schwiderski-Grosche (opens in new tab)<\/span><\/a>, Principal Research Program Manager<\/em><\/p>\n

As we move from narrow AI to more general AI, it will be important to instill machines with the ability to work together with both other agents and humans. Project Malmo (opens in new tab)<\/span><\/a>, which is built on the popular multiplayer game Minecraft, is an AI research tool for investigating how to train intelligent agents to collaborate. Our recent Project Malmo Collaborative AI Challenge (opens in new tab)<\/span><\/a> asked teams to solve a game using collaborative agents, a project designed to push the state of the art of collaborative AI.<\/p>\n

\"\"<\/p>\n

Katja Hofmann, the lead and visionary for Project Malmo, summarizes the intent of this challenge: \u201cIn Minecraft, the possibilities for creation are endless. Project Malmo adds the ability to try different methods and approaches to teaching an agent to work within the Minecraft framework. The challenge then gave teams a specific task to demonstrate an agent\u2019s ability to predict or learn whether to collaborate and how to collaborate successfully. From this challenge, we learned lots about various strategies for developing collaborative AI, such as planning-based approaches, deep neural network-based approaches, and co-evolution approaches.\u201d<\/p>\n

We were gratified that more than 80 teams comprising postgraduate students from 26 countries entered the challenge which required the teams to create and train agents to play a collaborative minigame \u2014 catch the pig \u2014 in which players work together to achieve a common goal. We selected this challenge because it mirrors the game theoretic \u201cstag hunt,\u201d a classic example that models the trade-offs between choosing to work together or go solo. We wanted to see how participants would approach this problem, what algorithms and strategies perform well today, and identify promising directions for future research.<\/p>\n

Each team had to submit their code to GitHub (opens in new tab)<\/span><\/a>, send in a write-up about their approach, and create a video showing their agent in action. Prizes for winning the challenge included a placement at the invitation-only Microsoft Research AI Summer School (opens in new tab)<\/span><\/a> and\/or Microsoft Azure for Research grants (opens in new tab)<\/span><\/a>, worth up to $20,000 USD. Winners were selected based upon several criteria, including the ability of their agents to achieve high game scores consistently, and the novelty and creativity of the teams\u2019 approaches.<\/p>\n

Today we\u2019re pleased to announce the winners with three teams winning prizes in both categories.<\/p>\n

Microsoft Research AI Summer School placement prize winners<\/h2>\n

This prize provides winners with a slot at our Microsoft Research AI Summer School, where PhD students work alongside Microsoft Research scientists in Cambridge. Attendees learn general research skills, get to know the MSR Cambridge Lab and enjoy the opportunity to network with leading AI research leaders.<\/p>\n

First place: <\/em><\/p>\n