在幻想文本冒险游戏中学习说话和行动
Learning to Speak and Act in a Fantasy Text Adventure Game
摘要:
我们介绍了一个大规模的众包文本冒险游戏作为研究平台,研究接地对话。在其中,代理人可以感知,表达和行动,同时与其他代理人进行对话。模型和人类都可以在游戏中扮演角色。我们描述了在这种情况下训练最先进的生成和检索模型的结果。我们表明,除了使用过去的对话,这些模型能够有效地使用底层世界的状态来调节他们的预测。特别是,我们表明,接地的本地环境的细节,包括位置描述,和对象(及其启示)和字符(及其以前的行动),它允许更好地预测代理的行为和对话。我们分析了在这种情况下成功接地所需的成分,以及这些因素中的每一个如何与能够成功说话和行动的代理人相关。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。