How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds

Prithviraj Ammanabrolu, Jack Urbanek, Margaret Li, Arthur Szlam, Tim Rocktäschel, Jason Weston


Abstract
We seek to create agents that both act and communicate with other agents in pursuit of a goal. Towards this end, we extend LIGHT (Urbanek et al. 2019)—a large-scale crowd-sourced fantasy text-game—with a dataset of quests. These contain natural language motivations paired with in-game goals and human demonstrations; completing a quest might require dialogue or actions (or both). We introduce a reinforcement learning system that (1) incorporates large-scale language modeling-based and commonsense reasoning-based pre-training to imbue the agent with relevant priors; and (2) leverages a factorized action space of action commands and dialogue, balancing between the two. We conduct zero-shot evaluations using held-out human expert demonstrations, showing that our agents are able to act consistently and talk naturally with respect to their motivations.
Anthology ID:
2021.naacl-main.64
Original:
2021.naacl-main.64v1
Version 2:
2021.naacl-main.64v2
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
807–833
Language:
URL:
https://aclanthology.org/2021.naacl-main.64
DOI:
10.18653/v1/2021.naacl-main.64
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.64.pdf
Optional supplementary data:
 2021.naacl-main.64.OptionalSupplementaryData.zip