Learning to Speak and Act in a Fantasy Text Adventure Game
We introduce a large scale crowdsourced text adventure game as a research platform for studying grounded dialogue. In it, agents can perceive, emote, and act whilst conducting dialogue with other agents. Models and humans can both act as characters within the game. We describe the results of training state-of-the-art generative and retrieval models in this setting. We show that in addition to using past dialogue, these models are able to effectively use the state of the underlying world to condition their predictions. In particular, we show that grounding on the details of the local environment, including location descriptions, and the objects (and their affordances) and characters (and their previous actions) present within it allows better predictions of agent behavior and dialogue. We analyze the ingredients necessary for successful grounding in this setting, and how each of these factors relate to agents that can talk and act successfully.
Code (1)
Tasks
RetrievalSimilar Papers 제목 키워드 기반
Text-based Adventures of the Golovin AI Agent
The domain of text-based adventure games has been recently established as a new challenge of creating the agent that is both able to understand natural language, and acts intelligently in text-described environments. I…
AI AgentSituated Dialogue Learning through Procedural Environment Generation
We teach goal-driven agents to interactively act and speak in situated environments by training on generated curriculums. Our agents operate in LIGHT (Urbanek et al. 2019)---a large-scale crowd-sourced fantasy text adven…
Situated Dialogue Learning through Procedural Environment Generation
We teach goal-driven agents to interactively act and speak in situated environments by training on generated curriculums. Our agents operate in LIGHT (Urbanek et al. 2019) -- a large-scale crowd-sourced fantasy text adve…
Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent
Contrary to most natural language processing research, which makes use of static datasets, humans learn language interactively, grounded in an environment. In this work we propose an interactive learning procedure called…
Grounded language learningToward Automated Quest Generation in Text-Adventure Games
Interactive fictions, or text-adventures, are games in which a player interacts with a world entirely through textual descriptions and text actions. Text-adventure games are typically structured as puzzles or quests wher…