Learning Dynamic Belief Graphs to Generalize on Text-Based Games

• URL: http://arxiv.org/abs/2002.09127v4
• Date: Tue, 11 May 2021 14:02:27 GMT
• Title: Learning Dynamic Belief Graphs to Generalize on Text-Based Games
• Authors: Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre C\^ot\'e, Mikul\'a\v{s} Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William L. Hamilton
• Abstract summary: Playing text-based games requires skills in processing natural language and sequential decision making. In this work, we investigate how an agent can plan and generalize in text-based games using graph-structured representations learned end-to-end from raw text.
• Score: 55.59741414135887
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Playing text-based games requires skills in processing natural language and sequential decision making. Achieving human-level performance on text-based games remains an open challenge, and prior research has largely relied on hand-crafted structured representations and heuristics. In this work, we investigate how an agent can plan and generalize in text-based games using graph-structured representations learned end-to-end from raw text. We propose a novel graph-aided transformer agent (GATA) that infers and updates latent belief graphs during planning to enable effective action selection by capturing the underlying game dynamics. GATA is trained using a combination of reinforcement and self-supervised learning. Our work demonstrates that the learned graph-based representations help agents converge to better policies than their text-only counterparts and facilitate effective generalization across game configurations. Experiments on 500+ unique games from the TextWorld suite show that our best agent outperforms text-based baselines by an average of 24.2%.

Related papers

• Dynamic Typography: Bringing Text to Life via Video Diffusion Prior [73.72522617586593]
  We present an automated text animation scheme, termed "Dynamic Typography" It deforms letters to convey semantic meaning and infuses them with vibrant movements based on user prompts. Our technique harnesses vector graphics representations and an end-to-end optimization-based framework.
  arXiv  Detail & Related papers  (2024-04-17T17:59:55Z)
• GRENADE: Graph-Centric Language Model for Self-Supervised Representation Learning on Text-Attributed Graphs [22.282756544376493]
  We develop a novel Graph-Centric Language model, GRENADE, to solve the problem of self-supervised representation learning on text-attributed graphs. GRENADE exploits the synergistic effect of both pre-trained language model and graph neural network by optimizing with two specialized self-supervised learning algorithms. The proposed graph-centric self-supervised learning algorithms effectively help GRENADE to capture informative textual semantics as well as structural context information on text-attributed graphs.
  arXiv  Detail & Related papers  (2023-10-23T17:18:35Z)
• 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)
• Commonsense Knowledge from Scene Graphs for Textual Environments [6.617487928813374]
  We investigate the advantage of employing commonsense reasoning obtained from visual datasets such as scene graph datasets. Our proposed methods have higher and competitive performance than existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-10-19T03:09:17Z)
• Generalization in Text-based Games via Hierarchical Reinforcement Learning [42.70991837415775]
  We introduce a hierarchical framework built upon the knowledge graph-based RL agent. In the high level, a meta-policy is executed to decompose the whole game into a set of subtasks specified by textual goals. In the low level, a sub-policy is executed to conduct goal-conditioned reinforcement learning.
  arXiv  Detail & Related papers  (2021-09-21T05:27:33Z)
• Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games [64.11746320061965]
  We study reinforcement learning for text-based games, which are interactive simulations in the context of natural language. We aim to conduct explicit reasoning with knowledge graphs for decision making, so that the actions of an agent are generated and supported by an interpretable inference procedure. We extensively evaluate our method on a number of man-made benchmark games, and the experimental results demonstrate that our method performs better than existing text-based agents.
  arXiv  Detail & Related papers  (2020-10-22T12:40:22Z)
• Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning [94.50608198582636]
  Interactive Fiction (IF) games with real human-written natural language texts provide a new natural evaluation for language understanding techniques. We take a novel perspective of IF game solving and re-formulate it as Multi-Passage Reading (MPRC) tasks.
  arXiv  Detail & Related papers  (2020-10-05T23:09:20Z)
• Predicting Strategic Behavior from Free Text [38.506665373140876]
  We study the connection between messaging and action in an economic context, modeled as a game. We introduce the study of an individual's action prediction in a one-shot game based on free text he/she provides. We employ transductive learning to predict actions taken by these individuals in one-shot games based on these attributes.
  arXiv  Detail & Related papers  (2020-04-06T20:05:30Z)
• Exploration Based Language Learning for Text-Based Games [72.30525050367216]
  This work presents an exploration and imitation-learning-based agent capable of state-of-the-art performance in playing text-based computer games. Text-based computer games describe their world to the player through natural language and expect the player to interact with the game using text. These games are of interest as they can be seen as a testbed for language understanding, problem-solving, and language generation by artificial agents.
  arXiv  Detail & Related papers  (2020-01-24T03:03:51Z)

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.