Grounding Language to Entities for Generalization in Reinforcement Learning

no code implementations • 1 Jan 2021 • H. J. Austin Wang, Karthik R Narasimhan

EMMA is end-to-end differentiable and can learn a latent grounding of entities and dynamics from text to observations using environment rewards as the only source of supervision.

reinforcement-learning Reinforcement Learning (RL) +1