Timezone: »

Hierarchical Decision Making by Generating and Following Natural Language Instructions
Hengyuan Hu · Denis Yarats · Qucheng Gong · Yuandong Tian · Mike Lewis

Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #175

We explore using latent natural language instructions as an expressive and compositional representation of complex actions for hierarchical decision making. Rather than directly selecting micro-actions, our agent first generates a latent plan in natural language, which is then executed by a separate model. We introduce a challenging real-time strategy game environment in which the actions of a large number of units must be coordinated across long time scales. We gather a dataset of 76 thousand pairs of instructions and executions from human play, and train instructor and executor models. Experiments show that models using natural language as a latent variable significantly outperform models that directly imitate human actions. The compositional structure of language proves crucial to its effectiveness for action representation. We also release our code, models and data.

Author Information

Hengyuan Hu (Facebook)
Denis Yarats (New York University)
Qucheng Gong (Facebook AI Research)
Yuandong Tian (Facebook AI Research)
Mike Lewis (Facebook AI Research)

More from the Same Authors