UXP_FB_Logo copy.jpg

News

Facebook's role-playing game teaches AI to complete tasks by reading descriptions

Facebook's role-playing game teaches AI to complete tasks by reading descriptions

Facebook's role-playing game teaches AI to complete tasks by reading descriptions

Facebook's role-playing game teaches AI to complete tasks by reading descriptions

By Kyle Wiggers

April 30, 2020

Originally Published Here

Summary

Demonstrating once again the potential of video games to advance AI and machine learning research, Facebook researchers propose a game-like language challenge - Read to Fight Monsters - in a paper that the International Conference on Learning Representations 2020 accepted.

RTFM tasks an AI agent plopped in a procedurally generated environment to learn the dynamics by reading a description of them, so that it can generalize to new worlds with dynamics it isn't familiar with.

Facebook's work could form the cornerstone of AI models capable of capturing the interplay among goals, documents, and observations in complex tasks.

At the beginning of a run, RTFM generates a large number of dynamics along with descriptions of those dynamics and goals.

Groups, monsters, modifiers, and elements are randomized, as are monsters' team assignments and the effectiveness of modifiers against various elements.

One element, team, and a monster from that team are designated to be the "Target" monster, while an element, team, and monster from a different team are designated a "Distractor" monster, along with an element that defeats the distractor monster.

The position of the target and distractor monsters - both of which move to attack the agent at a fixed speed - are also randomized so that the agent can't memorize their patterns.

Human-written templates indicate which monster belongs to which team, which

modifiers are effective against which element, and which team the agent should defeat.

The researchers leveraged reinforcement learning, a technique that spurs agents toward goals via rewards, to train an RTFM model they refer to as txt2π.

The team ran experiments in which they trained txt2π for a minimum of 50 million frames.

Reference

Wiggers, K. (2020, April 30). Facebook's role-playing game teaches AI to complete tasks by reading descriptions. Retrieved May 1, 2020, from https://venturebeat.com/2020/04/30/facebook-rpg-teaches-ai-to-complete-tasks-by-reading-descriptions/