Learning Knowledge Graph-based World Models of Textual Environments
- URL: http://arxiv.org/abs/2106.09608v1
- Date: Thu, 17 Jun 2021 15:45:54 GMT
- Title: Learning Knowledge Graph-based World Models of Textual Environments
- Authors: Prithviraj Ammanabrolu, Mark O. Riedl
- Abstract summary: This work focuses on the task of building world models of text-based game environments.
Our world model learns to simultaneously: (1) predict changes in the world caused by an agent's actions when representing the world as a knowledge graph; and (2) generate the set of contextually relevant natural language actions required to operate in the world.
- Score: 16.67845396797253
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: World models improve a learning agent's ability to efficiently operate in
interactive and situated environments. This work focuses on the task of
building world models of text-based game environments. Text-based games, or
interactive narratives, are reinforcement learning environments in which agents
perceive and interact with the world using textual natural language. These
environments contain long, multi-step puzzles or quests woven through a world
that is filled with hundreds of characters, locations, and objects. Our world
model learns to simultaneously: (1) predict changes in the world caused by an
agent's actions when representing the world as a knowledge graph; and (2)
generate the set of contextually relevant natural language actions required to
operate in the world. We frame this task as a Set of Sequences generation
problem by exploiting the inherent structure of knowledge graphs and actions
and introduce both a transformer-based multi-task architecture and a loss
function to train it. A zero-shot ablation study on never-before-seen textual
worlds shows that our methodology significantly outperforms existing textual
world modeling techniques as well as the importance of each of our
contributions.
Related papers
- Bridging Local Details and Global Context in Text-Attributed Graphs [62.522550655068336]
GraphBridge is a framework that bridges local and global perspectives by leveraging contextual textual information.
Our method achieves state-of-theart performance, while our graph-aware token reduction module significantly enhances efficiency and solves scalability issues.
arXiv Detail & Related papers (2024-06-18T13:35:25Z) - Learning to Model the World with Language [100.76069091703505]
To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world.
Our key idea is that agents should interpret such diverse language as a signal that helps them predict the future.
We instantiate this in Dynalang, an agent that learns a multimodal world model to predict future text and image representations.
arXiv Detail & Related papers (2023-07-31T17:57:49Z) - Foundational Models Defining a New Era in Vision: A Survey and Outlook [151.49434496615427]
Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world.
The models learned to bridge the gap between such modalities coupled with large-scale training data facilitate contextual reasoning, generalization, and prompt capabilities at test time.
The output of such models can be modified through human-provided prompts without retraining, e.g., segmenting a particular object by providing a bounding box, having interactive dialogues by asking questions about an image or video scene or manipulating the robot's behavior through language instructions.
arXiv Detail & Related papers (2023-07-25T17:59:18Z) - Tachikuma: Understading Complex Interactions with Multi-Character and
Novel Objects by Large Language Models [67.20964015591262]
We introduce a benchmark named Tachikuma, comprising a Multiple character and novel Object based interaction Estimation task and a supporting dataset.
The dataset captures log data from real-time communications during gameplay, providing diverse, grounded, and complex interactions for further explorations.
We present a simple prompting baseline and evaluate its performance, demonstrating its effectiveness in enhancing interaction understanding.
arXiv Detail & Related papers (2023-07-24T07:40:59Z) - Knowledge-enhanced Agents for Interactive Text Games [16.055119735473017]
We propose a knowledge-injection framework for improved functional grounding of agents in text-based games.
We consider two forms of domain knowledge that we inject into learning-based agents: memory of previous correct actions and affordances of relevant objects in the environment.
Our framework supports two representative model classes: reinforcement learning agents and language model agents.
arXiv Detail & Related papers (2023-05-08T23:31:39Z) - Infusing Commonsense World Models with Graph Knowledge [89.27044249858332]
We study the setting of generating narratives in an open world text adventure game.
A graph representation of the underlying game state can be used to train models that consume and output both grounded graph representations and natural language descriptions and actions.
arXiv Detail & Related papers (2023-01-13T19:58:27Z) - A Systematic Survey of Text Worlds as Embodied Natural Language
Environments [0.76146285961466]
Text Worlds are virtual environments for embodied agents that, unlike 2D or 3D environments, are rendered exclusively using textual descriptions.
These environments offer an alternative to higher-fidelity 3D environments due to their low barrier to entry.
arXiv Detail & Related papers (2021-07-08T22:15:16Z) - Modeling Worlds in Text [16.67845396797253]
We provide a dataset that enables the creation of learning agents that can build knowledge graph-based world models of interactive narratives.
Our dataset provides 24198 mappings between rich natural language observations and knowledge graphs.
The training data is collected across 27 games in multiple genres and contains a further 7836 heldout instances over 9 additional games in the test set.
arXiv Detail & Related papers (2021-06-17T15:02:16Z) - Situated Language Learning via Interactive Narratives [16.67845396797253]
This paper explores the question of how to imbue learning agents with the ability to understand and generate contextually relevant natural language.
Two key components in creating such agents are interactivity and environment grounding.
We discuss the unique challenges a text games' puzzle-like structure combined with natural language state-and-action spaces provides.
arXiv Detail & Related papers (2021-03-18T01:55:16Z) - Wandering Within a World: Online Contextualized Few-Shot Learning [62.28521610606054]
We aim to bridge the gap between typical human and machine-learning environments by extending the standard framework of few-shot learning to an online setting.
We propose a new prototypical few-shot learning based on large scale indoor imagery that mimics the visual experience of an agent wandering within a world.
arXiv Detail & Related papers (2020-07-09T04:05:04Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.