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

10/01/2020
by   Prithviraj Ammanabrolu, et al.
21

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.

READ FULL TEXT

page 2

page 17

page 18

page 25

page 26

page 27

10/07/2021

Situated Dialogue Learning through Procedural Environment Generation

We teach goal-driven agents to interactively act and speak in situated e...
03/07/2019

Learning to Speak and Act in a Fantasy Text Adventure Game

We introduce a large scale crowdsourced text adventure game as a researc...
09/20/2018

Teaching Social Behavior through Human Reinforcement for Ad hoc Teamwork -The STAR Framework

As technology develops, it is only a matter of time before agents will b...
02/07/2020

I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-orientated dialogue agents

Dialogue research tends to distinguish between chit-chat and goal-orient...
02/07/2020

I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-oriented dialogue agents

Dialogue research tends to distinguish between chit-chat and goal-orient...
07/14/2022

K-level Reasoning for Zero-Shot Coordination in Hanabi

The standard problem setting in cooperative multi-agent settings is self...
09/20/2018

Ad hoc Teamwork and Moral Feedback as a Framework for Safe Agent Behavior

As technology develops, it is only a matter of time before agents will b...