[GATA] Learning Dynamic Belief Graphs to Generalize on Text-Based Games | AISC
10For slides and more information on the paper, visit https://ai.science/e/gata-learning-dynamic-belief-graphs-to-generalize-on-text-based-games--Ubf3kPJc5FKPer1s3BhH
Speaker: Pascal Poupart; Host: Susan Shu Chang
Motivation:
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%.
------
#AISC hosts 3-5 live sessions like this on various AI research, engineering, and product topics every week! Visit https://ai.science for more details