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 (RTFM) — in a paper accepted by the International Conference on Learning Representations (ICLR) 2020. RTFM tasks an AI agent plopped into a procedurally generated environment with learning its dynamics by reading a description of them so 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 between goals, documents, and observations in complex tasks. If the RTFM agents perform well on objectives requiring reasoning, it could suggest language understanding is a promising way to learn policies — i.e., heuristics that suggest a set of actions in response to a state.
Unlock premium content and VIP community perks with GB M A X! Join now to enjoy our free and premium perks.
Join now →
Sign in to your account.