paper-with-me

홈 › Papers

Learning to Speak and Act in a Fantasy Text Adventure Game

2019-03-07 · IJCNLP 2019 11 · Jack Urbanek, Angela Fan, Siddharth Karamcheti, Saachi Jain, Samuel Humeau, Emily Dinan, Tim Rocktäschel, Douwe Kiela, Arthur Szlam, Jason Weston

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.

📄 PDF Abstract BibTeX arXiv:1903.03094

Code (1)

facebookresearch/light 공식 구현

Tasks

Retrieval

Similar Papers 제목 키워드 기반

Text-based Adventures of the Golovin AI Agent

2017-05-16 · Bartosz Kostka, Jaroslaw Kwiecien, Jakub Kowalski, Pawel Rychlikowski

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 Agent

Situated Dialogue Learning through Procedural Environment Generation

2021-11-16 · ACL ARR November 2021 11 · Anonymous

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

2021-10-07 · ACL 2022 5 · Prithviraj Ammanabrolu, Renee Jia, Mark O. Riedl

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

2017-11-21 · ICLR 2018 1 · Zhilin Yang, Saizheng Zhang, Jack Urbanek, Will Feng 외

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 learning

Toward Automated Quest Generation in Text-Adventure Games

2019-09-13 · CCNLG (ACL) 2019 10 · Prithviraj Ammanabrolu, William Broniec, Alex Mueller, Jeremy Paul 외

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…